We propose a silviculture with a purely biological logic that takes soil into account. The article is divided into three parts: 1) presentation of the issue in the context of biodiversity and forest pro-tection; 2) impact of the soil functioning on forestry; 3) possible implementation of soil functioning in forestry practice, to support and protect a non-or minimally anthropized evolution of the forest. The first chapter illustrates the importance of the forest for the future of the planet and our human species, referring to recently published works on the topic of climate warming and biodiversity. The second illustrates the aspects that link soil dynamics to the silvogenetic cycle, focusing on the humipedon (organic and organo-mineral surface horizons, approximately the first 30 cm of forest soil), and more significant carbon storage in old forests since up to 2/3 is found in the soil. In the third chapter we consider the possibility of lengthening the forestry cycle, to allow the return of nutrients to the soil. Theoretical graphs and distribution models of the number of trees as a func-tion of diameter and age are reported, with examples of logging in uneven Alpine forests, with reference to Swiss fir-beech forests published on the Pro-Silva website.

To understand forest dynamics under today’s changing environmental conditions, it is important to analyze the state of forests at large scales. Forest inventories are not available for all regions, so it is important to use other additional sources of information, e.g. remote sensing observations. Increasingly, remotely sensed data based on optical instruments and airborne LIDAR are becoming widely available for forests. There is great potential in analyzing these measurements and gaining an understanding of forests state. In this work, we combine the new generation radiative transfer model mScope with the individual-based forest model FORMIND to generate reflectance spectra for forests. Combining the two models allows us to account for species diversity at different height layers in the forest. We compare the generated reflectances for forest stands in Finland, in the region of North Karelia, with Sentinel-2 measurements. We investigate which level of forest representation gives the best results. For the majority of the forest stands, we generated good reflectances with all levels forest representation compared to the measured reflectance. Good correlations were also found for the vegetation indices (especially NDVI with R²=0.62). This work provides a forward modelling tool for relating forest reflectance to forest characteristics. With this tool it is possible to generate a large set of forest stands with corresponding reflectances. This opens the possibility to understand how reflectance is related to succession and different forest conditions.

The compelling effects of climate change on forests may have been underestimated in the past few decades in practical forestry. Although the first attempts to draw attention to this complex problem appeared almost half a century ago, the debate has been conceptual rather than experimental and applicative. At first glance, the con-cerns were mainly related to sustainable forest management (SFM) issues, which obviously needed attention. Over time, the effects of climate change have been mainly considered in the context of the SFM; they started from various and somewhat different scales and goals. Over time, more research and awareness of the im-portance of SFM under the pressure of climate change have led to the development of a clearer field that can be defined as ‘adaptive forest management’ - to climate change. One of the characteristics of this discipline is to be featured by the absence of univocal methods and / or objectives to be pursued but to identify, verify, and adapt methods to the various climatic and forest types and conditions found in the field. Therefore, this work shows some phases of forest planning and management concepts and criteria over time and recalls some innovative and / or adaptive methods related to the approach to forest planning and management under climate change

The GFPMX projects forest area and stock, consumption, production, imports, exports, and prices of industrial roundwood, fuelwood, sawnwood, wood-based panels, wood-pulp, and paper and paperboard, in 180 countries, and currently from 2018 to 2070. The core principle of the model is the Cobweb theorem, according to which markets are not necessarily in equilibrium, but take some time to adjust to shocks, such as demand shifts, leading to oscillatory dynamics of prices and quantities. The paper presents the model structure and the estimation of its parameters from international statistics on production, trade, forest area, and forest stock. This is followed by an application of the GFPMX to the impact on the global forest sector of the economic recession caused by the COVID-19 pandemic.

The landscape image is the bridge of communication between people and forests, and the cut point of the supply-side reform of forest tourism products. The research collected 140 copies in total of forest landscape image drawings from non-art-major graduate students by randomly sampling during April and May, 2018, and constructed the landscape image conceptual model of forest by utilizing the landscape image sketching technique. The results showed that (1) In regard to linguistic knowledge, the natural landscape elements for instance, herbaceous plants, terrains, creatures, water and sky, and the broad-leaf forest objectively reflected not only the real forest landscape and the local native vegetation, but the variation of forest species with little attention. (2) On the perspective of spatial view, the sideways view indicated that graduate students preferred to watch forests at a moderate distance externally and few looked at forests internally. (3) In the view of self-orientation, the objective landscape indicated that graduate students preferred to demonstrate forest landscapes, they did not realize to interact with the environment. (4) On the aspect of social meaning, the scenic view and forest structure stated that graduate students preferred rural forest landscapes, not significantly for other special interests for forest. In conclusions, (1) the forest is thought to be a feature of people's life world and of rural scenes around homes, not an objective perception of the forest. (2) The forest is regarded as an important habitat for animals and a limited resource for people's life, production and recreation needs, into which people will go only to meet such needs. (3) The natural values of forests, like the ecology and aesthetics, etc. get more attention, while the social values of forests, like the life, production and culture receives rather low attention.

Regarding number of vehicles, forest roads are characterized by low traffic intensity, but on the other hand great values of ground pressure between wheels of timber truck units and forest road surface occur, often with pressures values above 80 kN which additionally causes damage of the upper and lower forest road layer. There are currently several methods for assessing condition of a forest road surface which are mainly used for assessing state of public roads, but can be used in forestry as well. Assessing condition of forest road surface was done by measuring vibrations with a specially developed software for Android OS installed on a Huawei MediaPad 7 Lite. Software measured vibrations in all three axes, coordinates of device, speed of the vehicle and time. Aim of this research was to determine accuracy of collected data so that this method can be used for scientific and practical purposes. Research was carried out on the segment of a forest road during driving a vehicle equipped with a measuring device. Tests were performed in both driving direction of the forest road segment with different measuring frequencies, tyre inflation pressures and driving speeds. Values of vibrations were classified and translated on a map of forest road together with devices’ measured coordinates. Vibration values were compared with places of recorded forest road surface damages. Research results show no significant difference in vibration values between 1 Hz and 10 Hz of measurement frequencies. Based on the analysis of collected data and obtained results, it is clear that it is possible to assess the condition of a forest road surface by measuring vibrations. The greatest values of vibrations were recorded on the most damaged parts of the forest road. Vibrations do not depend on tyre inflation pressure, but ranges of vibrations are decreasing with decreasing driving speed. Accuracy of collected data depends on GPS signal quality, so it is recommended that each segment of forest road is recorded twice so that location of damages on forest road can be confirmed with certainty.

Ponderosa pine is an integral part of the forested landscape in the western US; it is the dominant tree species on landscapes that provide critical ecosystem services. Moderate drought tolerance allows it to occupy the transition zone between forests and open woodlands and grasslands. Increases in stand density resulting from wildfire suppression, combined with lengthening, intensifying and more frequent droughts have resulted in reduced tree vigor and stand health in dry ponderosa pine throughout its range. To address a management need for efficient landscape-level surveys of forest health, we used Random Forests to develop an object-oriented classification of individual tree crowns (ITCs) into vigor classes using existing, agency acquired 4-band aerial imagery. Classes of tree vigor were based on quantitative physiological and morphological attributes established in a previous study. We applied our model across a landscape dominated by ponderosa pine with a variety of forest treatments to assess their impacts on tree vigor and stand health. We found that stands that were both thinned and burned had the lowest proportion of low vigor ITCs, and that stands treated before the 2014-2016 drought had lower proportions of low vigor ITCs than stands treated more recently (2016). Upland stands had significantly higher proportions of low vigor trees than lowland stands. Maps identifying the low vigor ITCs would assist managers in identifying priority stands for treatment and marking trees for harvest or retention. These maps can be created using already available imagery and GIS software.

Vibration monitoring is a critical aspect of assessing the health and performance of machinery and industrial processes. This study explores the application of machine learning techniques, specifically the Random Forest (RF) classification model, to predict and classify chatter—a detrimental self-excited vibration phenomenon—during machining operations. While sophisticated methods have been employed to address chatter, this research investigates the efficacy of a simplified RF model. The study leverages simulated vibration data, bypassing resource-intensive real-world data collection, to develop a versatile chatter detection model applicable across diverse machining configurations. The feature extraction process combines time-series features and Fast Fourier Transform (FFT) data features, streamlining the model while addressing challenges posed by feature selection. By focusing on the RF model’s simplicity and efficiency, this research advances chatter detection techniques, offering a practical tool with improved generalizability, computational efficiency, and ease of interpretation. The study demonstrates that innovation can reside in simplicity, opening avenues for wider applicability and accelerated progress in the machining industry.

The land use land cover (LULC) map is extensively employed for different purposes. The LULC maps provided by the Portuguese National Geographic Information System (SNIG) are not ideal for continuous assessment and regular scrutiny. Machine learning (ML) algorithms applied in remote sensing (RS) data has been proven effective in image classification, object detection, and semantic segmentation. Previous studies have shown that Random Forest (RF) and Support Vector Machine (SVM) consistently achieved high accuracy for land classification. In this study, the application of RF and SVM classifiers, and object-based (OBIA) and pixel-based (PBIA) approaches with Sentinel-2A imagery was evaluated using Google Earth Engine (GEE) platform for land cover classification of a burned area in the Serra da Estrela Natural Park (PNSE), Portugal. This aimed to detect the land cover change and closely observe the burned area and vegetation recovery after the 2022 wildfire. The combination of RF and OBIA achieved the highest accuracy in all evaluation metrics. At the same time, a comparison with the Normalized Difference Vegetation Index (NDVI) map and Conjunctural Land Occupation Map (COSc) of 2023 year indicated that the SVM and PBIA map resembled the maps better.

Road safety and the effectiveness of the transportation system as a whole are significantly impacted by driver comfort. Road surface quality can play a significant part in the driver’s comfort experienced on roads in any country. This study employs a Random Forest technique to examine the association between road roughness and drivers' comfort during long-distance driving. Using Random Forest, a dependable machine learning technique that can handle big datasets and detect nonlinear correlations, this work aims to shed light on the complex dynamics between road conditions and driver’s comfort. 1,048,576 rows of data from MIRANDA, an application developed at the University of Gustave Eiffel, were used in this study as part of the data collected from a probe vehicle. The data collected includes an International Roughness Index (IRI). The IRI thresholds offer a simple method for assessing driver comfort and road irregularity. While highlighting how uneven and uncomfortable the road is, the research's findings (Road Roughness: SD – 0.73; Driver's Comfort: - Mean, 10.01, SD – 0.64) also contribute to the standardization of road condition evaluation and maintenance communication. This finding is anticipated to aid in the development of strategies for improving the welfare of long-haul drivers and fixing road infrastructure to comply with standard road index, ultimately leading to the creation of more efficient and sustainable transportation systems.

Prescribed burning and other active forest management treatments have been proven to be essential for maintaining suitable habitat conditions for many wildlife species, including the federally endangered red-cockaded woodpecker (RCW). This study examines the perception of forest management treatments of recreation users participating in various activities (hunting, hiking/backpacking, camping, off-highway vehicle riding, and canoeing/kayaking) in terms of scenic beauty and recreation satisfaction. We used photographic images to capture various forest management treatments of different intensity levels and times after treatments, and assessed users’ perception of scenic beauty and recreation satisfaction. Results indicated variation among users participating in different recreation activities, but that good quality RCW habitat offered both higher scenic beauty and higher recreation satisfaction than poor quality habitat for most user groups. Finally, recreation satisfaction was statistically equal to perceived scenic beauty from both good and poor-quality RCW habitats for most of the user groups, thus suggesting the importance of scenic beauty on forest sites in determining recreation users’ attainment of visit satisfaction. Findings conclude that forest sites developed as good quality RCW habitat in the present state also offer quality experience to recreation users, thus supporting multi-objective forestry practices in public forests.

Logistic Regression and Random Forest are used to identify risk factors that influence traffic accident fatalities in the United Kingdom. The mean decrease accuracy was used to measure variable importance. The speed limit, police attendance and quarter had an increasing influence on accident fatalities. They had a mean decrease of 102.1669, 221.5322, and 120.894 respectively. The speed limit, had a parameter estimate of 0.0046902 and a standard deviation of 0.0004875. Light Conditions: Night had a parameter estimate of 1.2657635 and a standard deviation of 0.0118409. Road Type Round About had a parameter estimate of -0.4055796 and a standard deviation of 0.0210848. Police Attendance classified as Yes had a parameter of 0.8546232 and a standard deviation of 0.0151043. The best predictors were speed limit, police attendance and quarter since they had p values that were less than 0.05. The findings of the study indicated that logistic Regression had a higher accuracy rate 79.85% as compared to 64.00% for Random Forest. A split test was used and a standard deviation of 0.0010486 was obtained for the Logistic Regression model.

Trees provide key ecosystem services, but the health and sustainability of these plants is under increasing biotic and abiotic threat, including from the growing incidences of non-native invasive plant pests (including pathogens). The island of Ireland (Ireland and Northern Ireland) is generally accepted to have a high plant health status, in part due to its island status and because of the national and international regulations aimed at protecting plant health. To establish a baseline of the current pest threats to tree health for the island of Ireland, the literature and unpublished sources were reviewed to produce a dataset of pests of trees on the island of Ireland. The dataset contains 396 records of pests of trees on the island of Ireland, the majority of pests being arthropods and fungi, and indicating potentially more than 44 non-native pest introductions. The reliability of many (378) of the records was judged to be high, therefore the dataset provides a robust assessment of the state of pests of trees recorded on the island of Ireland. We analyse this dataset and review the history of plant pest invasions, including (i) discussion on notable native and non-native pests of trees, (ii) pest interceptions at borders and (iii) pests and climate change. The dataset establishes an important baseline for the knowledge of plant pests on the island of Ireland, and will be a valuable resource for future plant health research and policy making.

The prolonged lockdown imposed to contain the COVID-19 pandemic prevented many people from direct contact with nature and greenspaces, raising alarms for a possible worsening of mental health. This study investigates the effectiveness of a simple and affordable remedy for improving psychological well-being, based on audio-visual stimuli brought by a short computer video showing forest environments, with an urban video as a control. Randomly selected participants were assigned the forest or urban video, to look at and listen early in the morning, and filled questionnaires. In particular, the State-Trait Anxiety Inventory (STAI) Form Y, collected in baseline condition and at the end of the study, and the Part II of the Sheehan Patient Rated Anxiety Scale (SPRAS), collected every day immediately before and after watching the video. The virtual exposure to forest environments showed effective to reduce perceived anxiety levels in in people forced by lockdown in limited spaces and environmental deprivation. Although significant, the effects were observed only in the short term, highlighting the limitation of the virtual experiences. The reported effects might also represent a benchmark to disentangle the determinants of health effects due to real forest experiences, for example, the inhalation of biogenic volatile organic compounds (BVOC).

Depression is considered a widespread mental health problem worldwide. Moreover, anxiety symptoms are very closely related to depression patients, and it is known that the coexistence rate of depression and anxiety diagnosed simultaneously is high. Treatment and preventive management of depression and anxiety are essential for public health. Forest healing is attracting attention as a form of low-cost preventive medicine that is safe and has no side effects. However, although the physiological and psychological effects have been scientifically proven, it is insufficient to reveal a direct relationship between forest healing and depression. This study investigated the benefits of an urban forest healing program on depression and anxiety symptoms of depressive disorders. We employed a randomized controlled trial design. Forty-seven depression patients were randomly divided into an urban forest healing program group and a control group. Measures included the Montgomery-Asberg depression rating scale (MADRS), the Hamilton Anxiety Rating Scale (HARS), and the State-Trait Anxiety Inventory (STAI) questionnaires. Our results revealed that the combination of general treatment and forest healing programs for patients with depression is more effective in improving depression and anxiety than routine treatment alone. We expect our work to serve as a starting point for more sophisticated research in discussing the availability of non-pharmacological treatments in forest healing.

Since the 1960s, forest planners have used linear programming models to develop management plans for large, forested areas. Hundreds of academic papers have presented such models, incorporating multiple objectives, a growing diversity of management interventions, and uncertainty, among other things. Three basic ways to formulate these models have been used: Model I, III, and III. We define these models based on the sequence of management unit states represented by the variables. In Model I, variables represent a sequence of states from the beginning of the planning horizon to the end. In Model II, variables represent a sequence of states from one intervention to the next. Finally, in Model III, variables represent a single arc in a management unit’s decision tree, including only a beginning and an ending state. We formulate each type of model for a case study with three increasingly complex scenarios incorporating additional ecosystem services. Our results indicate that, despite requiring more variables and constraints, Model III requires the least time to formulate, largely because it has the least dense parameter matrix. Model II has the shortest solution times, with Model III close behind. Model I requires both the longest formulation and solution times.

This paper is a follow-up to a previous study that was conducted in a research forest and identified the optimal method for Diameter at Breast Height (DBH) estimation as a circular scanning and fitting ellipses to 4cm stem cross-sections at breast height. The aim of this study was to determine whether the identified method is applicable to natural boreal forests as well. The iPad Pro LiDAR scanner was used to acquire point clouds for 15 sites representing a range of natural boreal forest conditions in Ontario, Canada, and estimate DBH. The secondary objective was to determine if tested stand (Species composition, age, density, understory) or tree (Species, DBH) factors affected the accuracy of estimated DBH. Overall, estimated DBH values were within 1cm of actual DBH values for 78 of 133 measured trees (59%). An RMSE of 1.5cm (8.6%) was achieved. Stand age had a large effect (>0.15) on the accuracy of estimated DBH values, while density, understory, and DBH had moderate effects (0.05-0.14). No trend was identified between accuracy and stand age. Accuracy improved as understory density decreased and as tree DBH increased. Inertial Measurement Unit (IMU) and positional accuracy errors with the iPad Pro scanner limit the feasibility of using this device for forest inventories.

A land cover map of two arctic catchments, nearby the Abisko Scientific Research Station, was obtained from a classification of a Sentinel-2 satellite image and a ground survey performed in July 2022. The two contiguous catchments, Miellajokka and Stordalen, are covered by various ecotypes, from boreal forest to alpine tundra and peatland. The random forests algorithm correctly identified 88% of polygon pixels reserved for testing. The developed workflow relied solely on open source software and acquired ground observations. Space organization was directed by the altitude as demonstrated by the intersection of the land cover with the topography. Comparison between this new land cover map and previous ones based on data acquired between 2008 and 2011 shows some trends of vegetation cover evolution in response to climate change in the considered area.

In the research, we studied the typical functional plant traits and life forms of plants that colonize forest gaps. In the research, we analysed functional plant traits of plant species growing on five forest gaps in the Dinaric fir-beech forest in Slovenia. The forest gaps were created as a result of natural disturbances. We selected 18 functional plant traits, whose values were obtained from the BiolFlor database. With the help of the JUICE program, we calculated the frequency of its occurrence on individual forest gap for each functional plant trait. Then we calculated Sperman's correlation coefficient at p<0.05, between the occurrence of individual functional plant traits and single forest gap. We found out that forest gaps are mainly colonized by perennials and herbaceous perennials and hamephytes. These are plant species that begin to flower in June and July, bloom for two or three months and are pollinated by insects, mainly hover flys and wild bees. Characteristic of colonizing plant species is also that, in addition to reproducing by seeds and spores, they also reproduce vegetatively. Besides that, birds and forest mammals are the vectors of fruit and seed dispersal of colonizing plant species.

Severe seasonal droughts driven by global climate change significantly alter the cycling of carbon and nutrients in forest ecosystems through disturbing plant physiology and phenology, soil physicochemical properties, and soil microbial activity. While, the investigation into the impacts of floor mass and plant roots on soil microbial biomass within the context of recurrent seasonal droughts is still rare. To investigate the environmental determinants governing soil microbial biomass with the escalating severity of seasonal droughts, we conducted a study on soil microbial biomass in a comprehensive block experiment, which was manipulated to explore the interplay between floor mass and plant roots contributions, crossed with a factorial irrigation treatment, in a montane subtropical moist evergreen broad–leaved forest of southwestern China. Within control and watered plots, we respectively established four experimental subplots with plant roots and floor mass included (R+F+), plant roots included but floor mass excluded (R+F−), plant roots excluded but floor mass included (R−F+), and plant roots and floor mass excluded (R−F−) from June 2019 to May 2023. The study results revealed that soil microbial biomass as well as soil moisture, floor mass, and plant roots showed an apparent single–hump modal within one year. In the comparative analysis of soil microbial biomass fluctuation amplitudes across control and watered plots, a discernible disparity was observed, indicating that significant differences in microbial biomass dynamics between the respective experimental conditions. The pooled data revealed a statistically significant influence of seasonal drought, floor mass, plant roots, and their reciprocal interactions on the soil microbial biomass, highlighting these factors as pivotal determinants of microbial community dynamics. This study elucidates the interactive regulatory mechanisms by which seasonal drought, floor mass, and plant roots collectively modulate soil microbial biomass within tropical and subtropical forests, offering insights into the complex ecological processes governing microbial community dynamics. This interactive regulation might influence the trajectory of plant species and soil microbial communities, facilitating their adaptive development and evolutionary responses.

Following the adoption of the Kunming-Montreal Global Biodiversity Framework (KM-GBF), with the Convention on Biological Diversity serving as its guiding treaty, the European Union (EU) has just reached an agreement on an EU Nature Restoration Regulation. This study carries out a systematic cross-walk between the restoration regulation and the KM-GBF, focusing on their implications for forest ecosystems. This paper identifies areas of alignment, divergence, and potential gaps related to habitat restoration, species protection, climate resilience, and the sustainable use of natural resources. The methodology adopts a grounded approach, starting with the 23 targets outlined in the KM-GBF and proceeding to the 28 articles set out in the restoration regulation. The results highlight the need for better alignment between the KM-GBF, the restoration regulation, and other forest-relevant EU policy instruments. The study stresses the need for a coherent and integrated EU policy approach that can address the diverse challenges and policy objectives facing forests. It concludes that amendments to the restoration regulation have significantly diluted its potential impact, limiting the EU Members States accountability and ability to meet KM-GBF goals and targets. It further stresses the need for strategies that can reconcile divergent EU policy pathways, support forest management and restoration efforts, while aligning with global biodiversity objectives.

Unmanaged forest ecosystems play a critical role in addressing the ongoing climate and biodiversity crises. As there is no commercial interest in monitoring the health and development of such inaccessible habitats, low-cost assessment approaches are needed. We used a method combining RGB imagery acquired using an Unmanned Aerial Vehicle (UAV), Sentinel-2 data and field surveys to determine the carbon stock of an unmanaged forest in the UNESCO World Heritage Site wilderness area Dürrenstein-Lassingtal in Austria. The entry-level consumer drone (DJI Mavic Mini) and free of charge Sentinel-2 multispectral datasets were used for the evaluation. We merged the Sentinel-2 derived vegetation index NDVI with aerial photogrammetry data and used an orthomosaic and a Digital Surface Model (DSM) to map the extent of woodland in the study area. The Random Forest (RF) Machine Learning (ML) algorithm was used to classify land cover. Based on the acquired field data, the average carbon stock per hectare of forest was determined to be 371.423 ± 51.106 t of CO2 and applied to the ML-generated classification. An overall accuracy of 80.8% with a Cohen’s kappa value of 0.74 was achieved for the land cover classification, while the carbon stock of the living Above-Ground Biomass (AGB) was estimated with an accuracy of -1.0% (± 5.9%). In conclusion, the proposed approach demonstrated that the combination of low-cost remote sensing data and field work can predict above-ground biomass with high accuracy. The results and the estimation error distribution highlight the importance of accurate field data.

Forest resources are renewable,rational exploitation and utilization of forest resources are not only conducive to sustainable development of population, but also can obtain higher economic benefits. Based on actual timber harvesting problems,a combined harvesting model of timber and non-timber with nonlinear harvesting term was established.Firstly, using the qualitative theory of ordinary differential equations, the dynamic behavior of the model is studied, and the existence and stability of the equilibrium point of the model are proved .Secondly, the optimal control solution is obtained by using the optimal control theory.Finally, the optimal harvesting strategy of timber and non-timber products is given based on the numerical simulation results, which provides a certain theoretical basis for the sustainable development of forestry ecological economy.

The Suspended soils (which are also called canopy soil), associated with epiphytic plants in tropical forest canopies, have a very special type of biological cycle, morphological organization and ecological functional role. To date, only some features of these soils have been described for certain sectors of the tropics, in particular Southeast Asia. It was studies out whether the chemical composition and hydrological parameters depend significantly on the genesis of suspended soil, or they represent a single soil phenomenon with a certain supposed ecosystem function. Suspended soils are characterized by average values of hygroscopic moisture comparable with mineral soils. At the same time the maximum water holding capacity and field moisture capacity reaches hundreds and even thousands of percent which cannot but lead to mesophilization of the microclimate of the near-stem environments. In any case suspended soils are characterized by 4-10 higher values of hydrologic properties than mineral terrestrial soils of the same landscapes. The carbon content in suspended soil materials varied widely and was comparable with that of tropical forest litter and boreal peatlands . At the same time, tropical suspended soils are characterized by very low nitrogen content, which is reflected in very high carbon-to-nitrogen ratios. Such a values are typical of peats and forest litter and indicates a very low degree of humification of organic matter. Soil pH values tends to the acidic, and more often very acidic range. This corresponds well to the low content of labile forms of calcium and magnesium and corresponds to the oligotrophy of the soils. The content of mobile forms of phosphorus, potassium and ammonium nitrogen is extremely high in suspended soils. The high content of nutrients in tropical suspended soils is enormously high compared to forest soils of other climatic zones and should be noted as their most important attributive characteristic. Taking into account the high accumulative-sorption capacity of suspended soils, the low content of heavy metals in them indicates the absence of modern aerotechnogenic pollution of all the studied ecosystems. Thus, we are talking about a certain deficiency of heavy metals in the eluvial ecosystem of the tropical rain forest. This once again confirms the hypothesis that the essence of epiphytic soil formation was and is that the biotic cycle breaks away from the ground and moves evolutionarily into the middle and upper tiers of the tropical rainforest ecosystem. Tree trunks in this context represent vertically and subhorizontally oriented phase interfaces, similar to parent materials, and epiphytic soils are analogues of peat accumulations with extremely high water-holding capacity, which is of extremely important environmental significance.

The many strains of Cannabis spp. are associated with many effects on users and contain many different potentially psychoactive metabolites, but the links between metabolite profiles and user effects are unclear. Here we take a statistical approach to linking cause (i.e. metabolites) to effects in Cannabis spp. through the prism of strains, using quantitative data for metabolite composition and user effects. We find that species (indica vs. sativa) explains <2% of the variability in metabolite profiles, while strain explains 1/3 of variability, indicating species is nonindicative of metabolite composition, while strain is approximately indicative. Using random forests we generate a table of potential metabolite-effect links. We also find that effect-weighted metabolite composition can effectively be described in terms of four values representing the concentrations of pairs or triplets of particular compounds.

As people's consumption habits change, loan plays a crucial role in our modern society. It provides individuals who do not have sufficient money with funds to purchase residential property or start a business. However, for avoiding unpleasant loan defaults, all financial institutions will first assess the borrower's risk index. By predicting the default risk of the borrower to decide whether to lend money. Machine learning algorithms, including random forest, linear regression and so on, have been benefited most of the real-world applications. With the development of machine learning methods, this paper, based on the personal history loan data of an institution studies the loan default risk, and uses the random forest classification model to predict the possibility of loan default. The result showed that the accuracy of this method was 85.62%, which show its application ability of real-world loan prediction and benefits the manager to decide the degree of risk for loan grant.

The forest regeneration phase in Sweden commonly involves mechanical soil preparation followed by planting of Scots pine or Norway spruce seedlings. The prepared soil offers planting positions with different properties, including decreased damage by pine weevil (Hylobius abietis L.). Nitrogen fertilization can be applied at the time of planting to aid establishment of the seedlings. In this study we compared the effect of organic nitrogen-fertilization for different planting positions, and seedling sizes on early survival and growth of Scots pine and Norway spruce seedlings. The main planting positions were capped mound, hinge, and mineral soil. Seedlings planted close to organic material were categorized as “low quality positions”, since proximity to organic material increase pine weevil attraction. Higher mortality rates related to pine weevil damage were recorded for seedlings planted in the low-quality positions, regardless of seedling size or N-fertilization. Pine weevil attack rates increased with increasing seedling size. Growth was in general lowest in mineral soil positions. The effect of organic N-fertilization on growth was positive for spruce regardless of planting positions and seedling size, while depending on planting position and seedling size for pine, indicating that effects of organic N-fertilization depend on seedling species, -size and planting position.

The moist Afromontane forest of Ethiopia plays a crucial role in carbon storage and mitigating greenhouse gas (GHG) emissions. To guide effective conservation policies, it is essential to understand the relationship between species diversity and carbon storage in this unique ecosystem. Therefore, this study, aimed to evaluate the response of above-ground carbon (AGC) to species and functional diversity, and their effects on AGC in the Yayu Coffee Forest Biosphere Reserve (YCFBR). Using different plot sizes, we collected vegetation data from the core, buffer, and transitional zones of the reserve. We selected traits related to plant-life strategy, competition ability, response to disturbances, and climate change. Structural Equation Models (SEM) were employed to assess the effects of species diversity, functional diversity, and functional dominance on AGC. Data analysis was conducted using R software. Our results revealed that the effects of species richness on AGC were mediated through functional diversity and functional dominance, as demonstrated by both the full mediation and partial mediation models. This suggests that the selection effects and niche complementarity are mutually exclusive yet equally important for predicting AGC. The findings further indicate that functional diversity and functional dominance together accounted for a significant predictors of the AGC by 21% in the YCFBR. From a practical standpoint, findings highlight the importance of conserving species diversity as a means to maintain higher AGC in the tropical moist Afromontane forests. In conclusion, this research significantly contributes to scientific literature by providing valuable insights into the complex relationship between species diversity and carbon storage. The results emphasize the crucial role of functional diversity and dominance in predicting AGC, underscoring the importance of biodiversity conservation for climate mitigation efforts. These findings have practical implications for the development of effective conservation policies tailored to protect and sustain the carbon storage potential of this unique ecosystem.

Accurately assessing forest structure and maintaining up-to-date information about forest structure is crucial for various forest planning efforts, including the development of reliable forest plans and assessments of the sustainable management of natural resources. Field measurements traditionally applied to acquire forest inventory information (e.g., basal area, tree volume, and aboveground biomass) are labor-intensive and time-consuming. To address this limitation, remote sensing tech-nology has been widely applied in modeling efforts to help estimate forest inventory information. Among various remotely sensed data, LiDAR can potentially help describe forest structure. This study was conducted to estimate and map forest inventory information across the Talladega Na-tional Forest by employing ALS-derived data and aerial photography. The quality of predictive models was evaluated to determine whether additional remotely sensed data can help improve forest structure estimates. Additionally, the quality of general predictive models was compared to that of species-group models. This study confirms that quality level 2 LiDAR data was sufficient for developing adequate predictive models (R2adj. ranging between 0.71 and 0.82) when compared to the predictive models based on LiDAR and aerial imagery. Additionally, this study suggests that species-group predictive models were of higher quality than general predictive models. Lastly, landscape-level maps were created from the predictive models, and these may be helpful to plan-ners, forest managers, and landowners in their management efforts.

The challenge of missing data in scientific research prompts researchers to decide between imputing incomplete data or discarding observations, where discarding can lead to information loss. Various methods exist, from simple deletion to sophisticated approaches like Multiple Imputation (MI). However, these methods often fall short with high-dimensional datasets. Multiple Imputation by Chained Equations (MICE) and Random Forest (RF) proximity imputation offer promising alternatives. Therefore, in this paper, we propose integrating MICE with Bayesian random forest (BRF) to enhance imputation accuracy and predictive power, particularly in high-dimensional analyses. Our approach combines MICE’s efficiency with BRF’s robustness, offering a comprehensive solution to missing data challenges. By way of example, we provide empirical evaluations to validate its effectiveness using synthetic data of various missing data scenarios. The results from the simulations showed that the combination of BRF and MICE offered a promising strategy for high-dimensional analysis in the presence of missing data.

Forest resources are an important material basis for ecological protection and economic devel-opment, and are responsible for the dual mission of guaranteeing national ecological safety and grain safety. Forest land is an important carrier of forest resources, and forest landowner is a direct component of forest land management. Forest landowners’ willingness to engage in forest man-agement affects whether the important value function of forest resources can be implemented. Are there differences in the willingness and behavior of forest management between ethnic minority foresters and ordinary foresters? How to stimulate the forest management willingness and behavior of forest farmers in ethnic minority areas?These questions will be about the realization of the value of forest resources. Through the analysis of 185 questionnaires in Yunnan Province, this paper clarifies the current situation of forest management of forest farmers in minority areas. Then, using the Sustainable Livelihoods Framework, we select three indicators including the socio-economic at-tributes of individual farmers, the cognition and experience of forest landowners, and policy guidance. And we use the binary logistic regression model to analyze the factors affecting the willingness of forester to participate in forest management. Through the above analysis, we find that: (1) Forest landowners' willingness to engage in forest management in minority regions is relatively high, at 71.98%. (2) Individual farmers’ socioeconomic attributes have the most significant degree of influence on willingness to engage in forest management, while forest landowners' cognitive and related experiences, policy guidance and other related variables influence willingness to engage in forest management at the macro level. (3) Literacy has a significant positive contribution to man-agement intentions, while forest land area, living standard, whether they are compensated by public welfare forest, and whether they participate in the project of returning farmland to forest and grass have a significant negative effect on management intentions. (4) There are significant differences between forest landowners' willingness to engage in forest management and the influencing factors between minority regions and non-minority regions. Finally, we suggest to improve the willingness to engage in forest management and forestry industry development in minority regions through innovative management methods, concentrated and continuous large-scale management, en-couraging capital investment and driving forest landowners to "nearby employment", optimizing the logging quota system and raising the compensation standard for public welfare forests. This study has important practical significance for promoting the realization of forest ecological products value, consolidating the achievement of poverty alleviation in forest areas and realizing rural re-vitalization in China.

Under the “Korean emission trading system in the forestry sector (KETSF)” initiative, the South Korean government has developed several greenhouse gas (GHG) emissions reduction programs that include forestry activities as the cornerstones of the initiative. Forest management is deemed to be a major strategy to implement KETSF; this has been confirmed by most participants in the program, who have shown their preference for forest management projects as the most effective and encouraging strategy to participate in the KETSF program. For a successful implementation of KETSF projects is essential to explore methods that optimize the positive impacts of such strategies, thereby maximizing the economic returns and carbon stocks that result from the implementation of forest management activities. Thus, this study investigated several value-added KETSF projects in South Korea, which included simulated scenarios under two main forest management strategies: one based on an extension of the rotation age, and a second one based on reforestation with new species. Five forest management scenarios were examined and evaluated in their ability to maximize carbon stocks and economic returns. Based on the results, Scenarios 2 and 4 were identified as the best KETSF projects in terms of carbon stock increments. Additionally, the results indicated that projects including reforestation with new species added more economic value than projects that considered an extension of the rotation age. The study also revealed that KETSF projects generated revenue in both scenarios, by either extending the rotation age or by implementing reforestation with new species.

Due to climate change, droughts have been occurring more frequently in Germany in recent years. More frequent and prolonged drought affects the health of trees and increases the risk of forest fires. A large-scale forest fire broke out near Treuenbrietzen, Brandenburg, in the summer of 2018 in pine monospecific forests. In addition to evaluating the damage caused, future reforestation is discussed, which is related mainly to the expectations of the forest owners. A telephone survey of seven affected forest owners was conducted using a semi-structured guided interview. The results from our interview demonstrated the support of private forest owners for mixed forests over monospecific pine forests. Most forest owners do not prioritize economic benefit with the forest land as forestry was not the primary source of income. Instead, the ownership of the forest tends to be linked to idealistic, cultural, and family values. The motives for reforestation vary but are often externally influenced. Different goals of forest owners lead to the challenge of finding consensus among them. We conclude that forestry advice by the federal and state governments is essential, especially on how climate change can affect local forests, to sensitize private forest owners to this problem.

In light of the critical and emerging global challenge posed by the increasing frequency and severity of heatwaves in recent decades, this study demonstrates a practical and robust workflow that bridges the gap in understanding how the effective integration of remote sensing data with ground-based observations can facilitate a comprehensive assessment of spatiotemporal heatwave patterns and trends in the central region of Thailand. This research transcends traditional methods, utilizing air temperature (Tair) and satellite-derived land surface temperature (LST) data from 1981 to 2019. Results exhibit that an analysis of Tair indicates increasing daytime heatwaves in peri-urban areas, with significant trends in heatwave number (HWN), heatwave frequency (HWF), and heatwave duration (HWD), heatwave amplitude (HWA) rises in urban settings while nighttime heatwaves significantly intensify in rural locales. Notably, LST trends reveal varied patterns, with peri-urban areas showing marked daytime increases in heatwave magnitude (HWM), HWA, and HWF. Correlation analysis (p=0.05) highlights strong daytime associations between Tair and LST in rural (HWN, HWF, HWD, r&gt;0.90) and peri-urban (HWM, HWA, r&gt;0.65) regions. Overall, this study advances approaches to the adaptable measurement and spatial-temporal pattern of heatwave-related risk areas, providing insights for decision-makers to develop sustainable practices and strategies for climate change adaptation.

This study delves into the impact of artificial intelligence on students’ learning.The paper pioneers the use of kmeans classification to reduce the dimensionality of features before the classification process, which minimizes redundant information and computational overhead. This step is not commonly found in prior research.Firstly, a random forest model is established with “whether AI assistance was used to complete the paper” as the output, and various features as inputs. The analysis of the predictive accuracy when changing input features reveals the degree of influence of each feature on using AI to complete the paper. After feature selection, the remaining 6 features can still effectively predict the use of AI to complete the paper, indicating the representativeness of the extracted indicators. Subsequently, the PCA-K-means algorithm is employed to classify the use of artificial intelligence. PCA algorithm is used for dimensionality reduction of the extracted features to better characterize students’ use of AI. Three representative variables are selected, and the contribution of each feature is computed based on the factor loading matrix. Finally, the K-means algorithm is used to classify students based on the three dimensional features, showing that students can be effectively classified into 2 categories. The results indicate that the majority of students support the use of AI technology to enhance their abilities, although some students may only intend to use AI to cope with exams and similar tasks.

Traditional disease severity monitoring is subjective and inefficient. This study employs a Parrot multispectral sensor mounted on an unmanned aerial vehicle (UAV) to apply machine learning algorithms, such as Random Forest, for categorizing defoliation levels in R7-stage soybean plants. The research assesses the effectiveness of vegetation indices, spectral bands, and relative vegetation cover as input parameters, demonstrating that machine learning approaches combined with multispectral imagery can provide a more accurate and efficient assessment of Asian soybean rust in commercial soybean fields. The Random Forest algorithm exhibited satisfactory classification performance when compared to recent studies, achieving accuracy, precision, recall, F1-score, specificity and AUC values of 0.94, 0.92, 0.92, 0.92, 0.97 and 0.97, respectively. The input variables identified as most important for the classification model were the WDRVI and MPRI indices, the RedEdge and NIR bands, and relative vegetation cover, with the highest Gini importance index.

Tropical forests provide habitats for diverse flora and fauna. In addition, they are essential in regulating the climate while at the same time millions of people depend on them for their livelihoods. As seen by rising political commitment and worldwide promises to reduce rates of deforestation and boost restoration of degraded forest ecosystems, forests are becoming more widely acknowledged for their role as a nature-based solution to many sustainable development concerns. Understanding tropical forest dynamics and their conservation have so become more important. This study analyzed, the forest stand structure, tree species composition, abundance and diversity and the regeneration status of Londiani Forest. Londiani Forest is divided into three blocks, namely Kedowa, Chebewor and Londiani and from each of these blocks belt transects 25 m wide and 1 km long were established 100 m from the edge of the forest to reduce edge effects. At every 200 m along the transect, 25 m × 25 m quadrats were set up in which, an inventory of all tree species was done. For tree species that could not be identified in the field, the local name was provided by para-taxonomists who participated in the data collection and the species name was later identified with the help of a taxonomist or a manual of woody tree species of Londiani Forest. The diameter at breast height (DBH) was measured at 1.3 m from the ground using a diameter tape. Tree height was measured using a Suunto angular clinometer. A nested quadrat 5 m x 5 m quadrat within the 25 m x 25 m quadrat was used to sample saplings while a 1 m x 1 m quadrat was used for sampling seedlings. Regeneration status was assessed using the number of seedlings and saplings. Stumps of trees cut were counted including identifying tree species from which the tree stump was derived. Data from the quadrats were entered into Microsoft Excel. Total stem density, species density, basal area, species basal area, relative density and species diversity were determined. A total of 1,308 individual trees belonging to 34 different species from 24 families were recorded. Kedowa had the highest (27) species richness followed by Chebewor (19) then Londiani (14). There was a statistically significant difference in species richness among the three forest blocks (p<0.05). There were no statistically significant differences in the mean DBH (F=0.560; p=0.729) and height class distribution (F= 0.821, p=.558) among the three forest blocks. There was a statistically significant difference in stem density (F=12.22; p=0.005) and woody species diversity (F=0.32; p=0.001) within the three forests blocks. There was no statistically significant difference in the basal area distribution within the three forest blocks p>0.005. The similarity index ranged from 0.34 to 0.47. In all the forest blocks, there was evidence of seedlings and saplings indicating that there was regeneration. Results clearly show that while the Londiani Forest shows variation in characteristics, there is clear evidence that it is regenerating.

Historical forest management practices in the southwestern US have left forests prone to high intensity, stand-replacement fires. Effective management to reduce the cost and impact of forest-fire management and allow fires to burn freely without negative impact depends on detailed knowledge of stand composition, in particular, above-ground biomass (AGB). Lidar-based modeling techniques provide opportunities to reduce costs and increase ability of managers to monitor AGB and other forest metrics. Using Bayesian Model Averaging (BMA), we develop a regionally applicable lidar-based statistical model for Ponderosa pine and mixed conifer forest systems of the southwestern USA, using previously collected field data. The selected regional model includes a mid and low canopy height metric, a canopy cover, and height distribution term. It explains 72% of the variability in field estimates of AGB, and the RMSE of the two independent validation data sets are 23.25 and 32.82 Mg/ha. The regional model developed is structured in accordance with previously described models fit to local data, and performs equivalently to models designed for smaller scale application. Developing regional models for broad scale application provides a cost-effective, robust approach for managers to monitor and plan adaptively at the landscape scale.

Tropical forest and savanna biomes are pivotal in the functioning of the Earth system. Tropical forests are one of the largest terrestrial biosphere carbon pools, whereas savannas exchange carbon between the biosphere and atmosphere via frequent and extensive landscape fires. Both are biodiverse and under increasing threat due to land clearing and anthropogenic climate change. Reliable mapping of tropical forest and savanna is essential to provide understanding of how anthropogenic impacts are affecting the extent of these biomes. Using Google Maps satellite imagery, we manually classified 24,239 random points as forest, savanna, or anthropogenic landscapes within the tropics. Because fire and climate are correlated, we developed separate geospatial models to rank the importance of climate, topography, and human influence on vegetation present. This modelling confirmed that those areas with more fires had lower probabilities of tropical forest, that forest was most likely in areas with high mean annual rainfall with little seasonal variation in precipitation, and that anthropogenic factors disrupt this environmental predictability. We found there were environments where tropical forest and savanna were equally probable are geographically restricted. These relationships suggest that future drier climates projected under anthropogenic climate change, combined with clearing and burning that have reduced tropical forest extent to a subset of its theoretical distribution, will lead to irreversible loss of tropical forests. Our modelling provides global mapping that can be used track further changes to distribution of rainforests.

Tree biomass and diversity relationship in mixed forest impacts on forest ecosystem services provisions. Tree biomass yield is driven by several aspects such as species identity, site condition, stand density, tree age as well as tree diversity expressed as species mingling and structural diversity. By comparing diverse degrees of tree mixture in natural forests we can insight on the ecosystem services provision level and dynamic. Two monitoring sites in the Castilian Northern Plateau (Spain) have been analyzed to disentangle the relationships between biodiversity levels and tree biomass yield. Two permanent one ha squared plots were established at Llano de San Marugan and Valdepoza. In each plot all individual trees were measured (diameter and height), georeferenced and its species identity defined. Tree species in the two sites were Pinus sylvestris, Pinus nigra, Pinus pinea, Quercus pyrenaica, Quercus ilex, Quercus faginea and Juniperus thurifera. From these datasets ten diversity indices that fall in three categories (species richness indices, species compositional/mingling indices and vertical structural indices) were used as predictor variables to fit several candidate models. By merging the trees by site (without considering the species identity) selected models include individual tree basal area as explanatory variable combining by addition or interaction with diversity indices. When species are analyzed independently structural diversity impacts on biomass yield in combination (additive or multiplicative) with tree size is negative Pinus nigra and positive for the other species.

Background and Objectives: The site types of Eucalyptus urophylla × Eucalyptus grandis clonal plantations in southern Yunnan were compared, aiming to provide basis for site selection and scientific plantations management. Materials and Methods: In this study, 80 standard plots were set up in the 6−9-year-old Eucalypts plantations in Pu'er City and Lincang City. Furthermore, the quantitative theory I model and canonical correlation analysis were used to analyze the relationship between dominant tree growth traits and site factors, and evaluate the growth potential of E. urophylla × E. grandis plantation. Results: The multiple correlation coefficient between 8 site factors (altitude, slope, slope level, soil thickness, slope direction, texture, soil bulk density, and litter thickness) and the quantitative growth of the dominant wood was 0.825 (P < 0.05). According to the correlation coefficient of the quantitative regression model, slope, altitude, and soil thickness were the main factors for the classification of E. urophylla × E. grandis plantations in southern Yunnan. In addition, E. urophylla × E. grandis plantations grew best downhill and mid uphill at relatively low altitude, where the soil layer was thick and composed of weathered red soil. Contrastingly, E. urophylla × E. grandis plantation growth was extremely poor in uphill sites at higher altitude, where the soil layer was thin and composed of semi-weathered purple soil. Furthermore, total N, and available B, Cu, and Zn content, as well as soil organic matter content in the soil had a great influence on the growth of E. urophylla × E. grandis. Conclusions: Nitrogen and phosphate fertilizer as well as trace elements such as B, Zn, and Cu can be properly applied in middle- and low-yield forests to promote the growth and development of E. urophylla × E. grandis plantations.

Forest recreation can be successfully conducted for the purpose of psychological relaxation, as has been proven in previous scientific studies. During the winter in many countries, when snow cover occurs frequently, forest recreation (walking, relaxation, photography, etc.) is common. Nevertheless, whether forest therapy conducted in a forest environment with a snow cover will also have a positive effect on psychological indicators remains unknown. Furthermore, male subjects frequently participate in forest therapy experiments, whereas females are rarely involved. Thus, in this study, the effectuality of forest recreation during winter and with snow cover was tested on 32 young females. For these reasons, the experiment involved 15-minute periods of relaxation in a forest environment or in an urban environment, in addition to a pre-test under indoor conditions. Four psychological questionnaires (POMS, PANAS, ROS, SVS) were administered to participants before and after interventions. Results showed that participants’ levels of negative mood, as measured by different aspects of the POMS questionnaire (tension-anxiety, anger-hostility, depression-dejection, confusion, fatigue), decreased after exposure to the forest environment. In contrast, both tension-anxiety and anger-hostility increased in the urban environment. The indicator of negative affect from the PANAS questionnaire also increased after exposure to the urban environment, whereas the indicator of positive affect based on PANAS was higher in the forest environment than in the urban environment. Restorativeness and subjective vitality exhibited higher values after exposure to the forest environment in comparison to those from the control and pre-test. The changes in these indicators demonstrates that forest recreation in the snow during winter can significantly increase psychological relaxation in young females, as well as showing that recreation can be successfully conducted under these winter conditions.

Conifer bark beetles (Coleoptera: Curculionidae: Scolytinae) are major agents of natural disturbance in temperate forests of the northern hemisphere, capable of killing billions of trees in native forests. The dynamics of these insect populations are influenced by climatic variability. To understand such a relationship, it is necessary to monitor the population fluctuation of the species present over time. In this regard, the objective of the present study was to determine the species community of the genus Dendroctonus, the population fluctuation throughout the months of the year, and the effects of relative humidity, temperature, and precipitation on the fluctuation, at three sites of mixed forests in the Municipality of Bocoyna, Chihuahua, in northern Mexico. For insect monitoring, we used Lindgren funnel traps (with 8 funnels each) baited with semiochemicals. Every two weeks, and during 2 years, we collected, identified, and counted the insects. The identification of the species was based on the external morphology and characteristics of the male seminal rod. Temperature and relative humidity were measured using climate data loggers (HOBOs). We found six Dendroctonus species. We also determined the population fluctuation patterns of D. mexicanus Hopkins, D. frontalis Zimmermann, and D. brevicomis LeConte, species with the highest number of captures at each site. Additionally, the relationship between species abundance and climatic variables was determined. The variable that significantly influenced (P&lt;0.05) abundance was temperature. Relative humidity and precipitation variables did not show a significant relationship (P&gt;0.05).

This study evaluates the effectiveness of a Random Forest model for predicting above-ground biomass in South Carolina (SC), utilizing diverse remote sensing and climatic data sources. SC, with its humid subtropical climate and varied geography, including the Atlantic coastal plain, Piedmont, and Blue Ridge Mountains, poses unique challenges for biomass estimation. We integrated global biomass datasets for 2010, MODIS vegetation indices (NDVI and EVI), Leaf Area Index (LAI) from MOD15A2H, and climate data from TerraClimate. The model was trained using 2010 data and applied to 2022 datasets to assess biomass changes. To validate the model, plot-level biomass estimates from the 2023 FIA data were interpolated using Inverse Distance Weighting (IDW). Performance evaluation showed a strong positive correlation between predicted and observed biomass, with a correlation coefficient of 0.77 and an R² value of 0.62, indicating that the model explains 62% of the variability in biomass. Comparison with IDW-interpolated biomass data resulted in a correlation coefficient of 0.64, confirming the model's validity. Although the Random Forest model demonstrated reliable predictions, the study suggests potential improvements by incorporating additional data sources and advanced modeling techniques. The findings emphasize the value of integrating remote sensing data, machine learning, and interpolation methods to enhance biomass estimation accuracy. This research provides crucial insights into biomass distribution in SC and establishes a basis for future studies on forest monitoring and carbon accounting, highlighting the importance of combining various data sources for comprehensive environmental analysis.

We investigated the response of leaf photosynthetic capacity to climate warming and its variation among provenances of Larix gmelinii (Dahurian larch). Seedlings of 11 L. gmelinii provenances were transplanted into two common gardens with different climate conditions (control and warming climate). We measured the leaf photosynthetic capacity and explored its influencing factors. The warming treatment significantly increased the maximum net photosynthetic rate (Pmax-a), photosynthetic nitrogen use efficiency (PNUE), maximum carboxylation rate (Vcmax), maximum electron transport rate (Jmax), triose phosphate utilization rate (TPU), mesophyll conductance (gm), leaf nitrogen content (Narea), and chlorophyll content (Chlm). The Pmax-a was significantly positively associated with Vcmax, Jmax, TPU, gm, and Narea, and the slope of the correlations between Pmax-a and Vcmax, Jmax, and TPU was steeper in the warming treatment. The responses of Pmax-a, PNUE, Vcmax, Jmax, TPU, Narea, and Chlm to warming differed among provenances. The effects of warming on Pmax-a, Vcmax, Jmax, and TPU increased and then decreased as the aridity index of the original site increased. Overall, the warming treatment improved the photosynthetic capacity of L. gmelinii, but the extent of the improvement varied among provenances. These findings provide insights into the mechanisms underlying the responses of L. gmelinii to climate warming.

Antimicrobial peptides (AMPs) are considered as promising alternatives to conventional antibiotics in order to overcome the growing problems of antibiotic resistance. Computational prediction approaches receive an increasing interest to identify and design the best candidate AMPs prior to the in-vitro tests. In this study, we focused on the linear cationic peptides with non-hemolytic activity, which are downloaded from the Database of Antimicrobial Activity and Structure of Peptides (DBAASP). Referring to the MIC (Minimum inhibition concentration) values, we have assigned a positive label to a peptide if it shows antimicrobial activity; otherwise the peptide is labeled as negative. Here, we focused on the peptides showing antimicrobial activity against Gram-negative and against Gram-positive bacteria separately, and we created two datasets accordingly. Ten different physico-chemical properties of the peptides are calculated and used as features in our study. Following data exploration and data preprocessing steps, a variety of classification algorithms are used with 100-fold Monte Carlo Cross Validation to build models and to predict the antimicrobial activity of the peptides. Among the generated models, Random Forest has resulted in the best performance metrics for both Gram-negative dataset (Accuracy: 0.98, Recall: 0.99, Specificity: 0.97, Precision: 0.97, AUC: 0.99, F1: 0.98) and Gram-positive dataset (Accuracy: 0.95, Recall: 0.95, Specificity: 0.95, Precision: 0.90, AUC: 0.97, F1: 0.92) after outlier elimination is applied. This prediction approach might be useful to evaluate the antibacterial potential of a candidate peptide sequence before moving to the experimental studies.

A strategy to reduce qualitative and quantitative losses in crop-yields refers to early and accurate detection of insect-damage caused in plants. Remote sensing systems like hyperspectral proximal sensors are a promising strategy for managing crops. In this aspect, machine learning predictions associated with clustering techniques may be an interesting approach mainly because of its robustness to evaluate high dimensional data. In this paper, we model the spectral response of insect-herbivory-damage in maize plants and propose an approach based on machine learning and a clustering method to predict whether the plant is herbivore-attacked or not using leaf reflectance measurements. We differentiate insect-type damage based on the spectral response and indicate the most contributive wavelengths to perform it. For this, we used a maize experiment in semi-field conditions. The maize plants were submitted to three different treatments: control (health plants); plants submitted to Spodoptera frugiperda herbivory-damage, and; plants submitted to Dichelops melacanthus herbivory-damage. The leaf spectral response of all plants (controlled and submitted to herbivory) was measured with a FieldSpec 3.0 Spectroradiometer from 350 to 2500 nm for eight consecutive days. We evaluated the performance of different learners like random forest (RF), support vector machine (SVM), extreme gradient boost (XGB), neural networks (MLP), and measured the impact of a day-by-day analysis into the prediction. We proposed a novel framework with a ranking strategy, based on the accuracy returned by predictions, and a clusterization method based on a self-organizing map (SOM) to identify important regions in the reflectance measurement. Our results indicated that the RF-based framework algorithm is the overall best learner to deal with this type of data. After the 5th day of analysis, the accuracy of the algorithm improved substantially. It separated the three treatments into different groups with an F-measure equal to 0.967, 0.917, and 0.881, respectively. We also verified that the most contributive spectral regions are situated in the near-infrared domain. We conclude that the proposed approach with machine learning methods is adequate to monitor herbivory-damage of S. frugiperda and stink bugs like Dichelops melacanthus in maize, differentiating the types of insect-attack early on. We also demonstrate that the framework proposed for the analysis of the most contributive wavelengths is suitable to highlight spectral regions of interest.

The loss of native forests in Argentina has been a concern, driven by factors such as agriculture expansion and urbanization. Therefore, understanding the conservation status of sampled populations and their adaptation to different plant communities is essential. This research focused on the heterogeneity analysis of the associated woody and semi-woody vegetation to Hexachlamys edulis (O. Berg) Kausel & D. Legrand, a species commonly known as "ubajay," in Entre Ríos, Argentina. The study aimed to record the species present in the populations, explore plant communities associated with H. edulis and identify other potentially useful agroforestry species, compare locations based on the similarity of accompanying species, and explain the conservation status of each population. Results revealed a total of 71 species belonging to 39 families. Myrtaceae family was the most relevant, particularly in terms of native species representation. The analysis of biodiversity indicators, including richness, Shannon index and dominance revealed variations among the studied sites. The anthropic indicator highlighted the impact of human activity, with Concordia showing a higher ratio of native to exotic species. Cluster analysis and ordination techniques revealed groupings of censuses from the same localities, indicating differences in vegetation composition between sites. Significant differences in species composition were found among the sampled populations. Overall, the study can serve as baseline information for future research on the dynamics of vegetation in these areas and on H. edulis studied species. Finally, these findings contribute to understanding how wild species like H. edulis adapt to different plant communities, which might be valuable for developing new agroecological approaches or identifying potential companion planting species in future agricultural systems.

A primary challenge facing conservationists is reconciling the human needs of forest adjacent communities with the needs of conserving forest biodiversity, especially in tropical regions with growing populations of rural poor. Agroforestry has the potential to simultaneously provide for human needs and enhance forest biodiversity, but the complex interactions and feedbacks between the social and natural dimensions are relatively undescribed and thus systematic implementation is rare. The attributes of trees on farms required for human needs and conservation value may conflict. For example, exotic species in monoculture may provide the most economic value for farmers, while relic or planted indigenous tree mixtures may be more valuable for biological conservation. The objective of this study was to explore whether agroforestry practices in a moist tropical forest ecosystem in Kenya can simultaneously provide timber and fuelwood value to small-holder farmers while extending forest tree biodiversity. We described the agroforestry attributes on farms around a tropical forest, assessed the relationship between number and biomass of timber/fuelwood trees and tree biodiversity, and explored the relationships between forest tree diversity attributes and farm tree diversity attributes on a landscape scale using spatial analysis. We found that the diversity and number of trees on farms in this area are extensive yet variable, but that no significant relationship exists between the number of timber/fuelwood trees and tree diversity. This suggests that the two values of agroforestry may not be in conflict, due mainly to the high diversity of trees used for fuelwood. We also found that trees on farms in the larger landscape add to the conservation value of forest tree biodiversity and could be important components in conservation management. If agroforestry is to play an increasingly active role in conserving biodiversity in human-dominated landscapes, particularly in areas of dense subsistence farmer populations, increase recognition needs to be given to farmer’s perception of the value of trees and their selection of what trees to plant or maintain.

UAVs are becoming a crucial tool in modern warfare, primarily due to their cost-effectiveness, risk reduction, and ability to perform a wider range of activities. The use of autonomous UAVs to conduct strike missions against highly valuable targets is the focus of this research. Due to developments in ledger technology, smart contracts, and machine learning, such activities formerly carried out by professionals or remotely flown UAVs are now feasible. Our study provides the first in-depth analysis of challenges and potential solutions for successful implementation of an autonomous UAV mission.

The monitoring of fog density is of great importance in meteorology and its applications in environment, aviation and transportation. Nowadays, vision-based fog estimation from images taken with surveillance cameras has made a great supplementary contribution to the scarcely traditional meteorological fog observation. In this paper, we propose a new Random Forest (RF) approach for image-based fog estimation. In order to reduce the impact of data imbalance on recognition, the StyleGAN2-ADA (generative adversarial network with adaptive discriminator augmentation) algorithm is used to generate virtual images to expand the data of low proportions. Key image features related to fog are extracted, and an RF method, integrated with the hierarchical and k-medoids clustering, is deployed to estimate the fog density. The experiment conducted in Sichuan in February 2024 shows that the improved RF model has achieved an average accuracy of fog density observation to 93%, 6.4% higher than the RF model without data expansion, 3%-6% higher than the VGG16, the VGG19, the ResNet50, and the DenseNet169 with or without data expansion. What is more, the improved RF method exhibits a very good convergence as a cost-effective solution.

Mount Hamiding Protected Forest is located in North Halmahera Regency, North Maluku Province, the Wallace zone has an important role in providing protection functions, life support systems and regulating water management, preventing floods, preventing seawater intrusion, and controlling soil fertility. The protected forest area in the Wallace Zone is globally renowned for its endemic characteristics of flora and fauna. The condition of the protected forest of Mount Hamiding HMPF is currently experiencing anthropogenic damage as a result of forest encroachment, illegal logging, shifting cultivation, grazing and poaching to meet social needs. Anthropogenic damage has been in the spotlight for decades and has become a global issue. This study aims to determine damage to protected forests, changes in land cover, and mitigation of protected forest areas. This research uses quantitative and descriptive qualitative methods. Determination of research locations by purposive sampling. Parameters measured in this study were damage to protected forests, changes in land cover and area mitigation strategies. To identify forest damage, snowball sampling was carried out, and land cover changes through land cover data processing were obtained from the Ministry of Environment and Forestry of the Republic of Indonesia. Then using Imagery 7 ETM+ and 8 OLI to calculate changes in forested land to non-forested from 2006 -2021, analysis of land cover change using supervised classification, developing a strategy based on identity verification of forest damage and analysis of land cover change. The results showed that damage to protected forests was caused by anthropogenic disturbances in the form of forest encroachment, shifting cultivation, illegal logging, grazing and hunting of wild animals. Changes in land cover experienced the greatest damage in 2006-2021 amounting to 1,796.54 ha (16.17%). Strategic efforts are carried out using forest engineering, namely the agroforestry system and social engineering through community empowerment, namely training and outreach.

In the dynamic landscape of the telecommunications industry, understanding and mitigating customer churn is paramount for maintaining competitive advantage and sustaining revenue streams. This comprehensive literature review delves into the intricacies of customer churn prediction, a crucial aspect in fortifying the bond between telecom businesses and their customers. The review methodically analyzes 11 articles published between 2000 and March 2024, spotlighting the strategic role of Customer Relationship Management and the prevalence of high churn rates that necessitate a shift from customer acquisition to retention strategies. Furthermore, the review navigates through the challenges inherent in churn prediction, including the complexities of managing large, imbalanced, and noisy datasets and the intricacies involved in model selection and optimization. Despite these challenges, the paper highlights the superior capability of machine learning techniques in handling complex datasets to provide accurate predictions, albeit acknowledging their practical complexities. The main aim of the study is to provide an overview, serving as a knowledge base for researchers interested in machine learning techniques within the realm of telecommunications.

Forest recreation can be successfully used for the psychological relaxation of respondents and can be used as a remedy for common problems with stress. The special form of forest recreation intended for restoration is forest bathing. These activities might be distracted by some factors, such as viewing buildings in the forest or using a computer in nature, which interrupt psychological relaxation. One factor that might interrupt psychological relaxation is the occurrence of an open dump in the forest during an outdoor experience. To test the hypothesis that an open dump might decrease psychological relaxation, a case study was planned that used a randomized, controlled crossover design. For this purpose, two groups of healthy young adults viewed a control forest or a forest with an open dump in reverse order and filled in psychological questionnaires after each stimulus. A pretest was used. Participants wore oblique eye patches to stop their visual stimulation before the experimental stimulation, and the physical environment was monitored. The results were analyzed using the two-way repeated measures ANOVA. The measured negative psychological indicators significantly increased after viewing the forest with waste, and the five indicators of the Profile of Mood States increased: Tension-Anxiety, Depression-Dejection, Anger-Hostility, Fatigue, and Confusion. In addition, the negative aspect of the Positive and Negative Affect Schedule increased in comparison to the control and pretest. The measured positive indicators significantly decreased after viewing the forest with waste, the positive aspect of the Positive and Negative Affect Schedule decreased, and the Restorative Outcome Scale and Subjective Vitality scores decreased (in comparison to the control and pretest). The occurrence of an open dump in the forest might interrupt a normal restorative experience in the forest by reducing psychological relaxation. Nevertheless, the mechanism of these relevancies is not known, and thus, it will be further investigated. In addition, in a future study, the size of the impact of these open dumps on normal everyday experiences should be investigated. It is proposed that different mechanisms might be responsible for these reactions; however, the aim of this manuscript is to only measure this reaction. The identified psychological reasons for these mechanisms can be assessed in further studies.

The migration routes have facilitated the distribution of mammals from south east Asian mainland to the Sundaland including Java island in the early Pleistocene. One of species that has migrated through that route is antelope-like bovid Duboisia santeng. In the present study, the potential distribution areas and the suitable habitats of D. santeng have been projected and modeled. The modeled habitat was a forest river basin sizing 302.91 Ha in the central of Java island. The model has classified and reconstructed the habitat suitability ranged from low to high back to Pleistocene. The surrounding areas of forest were mostly classified as medium and low related to the limited tree covers. Most suitable habitats were identified in the middle of forest river basin where the tree covers were presented

The study sheds light on the impact of urbanization on fragile ecosystems such as the western Himalayas. We use Haldwani in Uttarakhand as an example of human encroachment and loss of ecosystem services. Several environmental parameters such as Nighttime light (NTL), Land Surface Temperatures (LSTs), Aerosol Optical Depth (AOD) and forest cover are used based on satellite imagery to allow a bidecadal comparison (between 2000 and 2020) of the status of these parameters for the city based on these parameters shows a decline in ecosystem services. Significant statistical differences for LSTs and AOD (p < 0.001) can be found in the bidecadal comparison. Furthermore, a strong negative correlation was found between LST-NDVI (r = -0.69) and between NTL-NDVI (r = -0.58) in earlier and last decade intervals. In addition, long-term multi-spectral satellite imagery also shows a decline in tree cover in the reserved forest. Therefore, focusing on ecosystem services related to tree cover in reserved forest areas, particularly in the Indian Himalayan Region (IHR) must be part of a broader action plan to address these issues to further protect fragile Himalayan ecosystems.

Forest fire is a major ecological disaster, which has economic, social and environmental impacts on humans and also causes the loss of biodiversity. Forest officials issue the warnings to the public on the basis of fire danger index classes. There is no fire danger index for the country India due to the sparsely distributed meteorological stations. Previous studies suggest that Static Fire Danger Index (SFDI) as well as Dynamic Fire Danger Index (DFDI) have been derived from the satellite datasets. In this study, we have made an attempt to integrate both the Static and Dynamic fire danger indices and also used the Near Real Time (NRT) data sets that can be available for download through NASA FTP server after one hour of the satellite overpass. In this study, DFDI has been calculated from the MODIS Terra NRT Land Surface Temperature (MOD11_L2) and MODIS TERRA NRT surface reflectance MOD09. Finally, The Forest Fire Danger Index (FFDI) has been developed from the static and dynamic fire danger indices by the additive model and the overall accuracy was around 81.27%. Thus, the FFDI has been useful to predict the fire danger accurately and can be useful anywhere, where the meteorological stations are un-available.

The evaluation of logging in a forest management area using only the volume variable is not sufficient to assess the effectiveness of the harvest. The objective was to evaluate harvested volume using different logging variables to point out possible divergences between what was planned and what was actually carried out, in order to indicate adjustments to next annual operating plans (AOPs). The database comes from a community forest management area in the Tapajós National Forest, considering three sources: forest inventory, AOP planning and the post-exploration report. The yield considering the number of trees felled and the effective volume were compared with the AOP planning. The volume estimated by the generic equation was compared with the cubed volume and the commercial height variable was evaluated. Of the 6,267 trees selected, 5,090 trees were harvested (3.2 trees ha^-1), indicating a yield of 85% of the estimated volume. Of the 25 commercial species logged, the most representative were: Manilkara huberi, Vochysia maxima, Lecythis lurida, Couratari guianensis and Hymenaea courbaril. It can be concluded that the number of trees, cubed volume and commercial height are post-exploration yield response variables and not just volume, as is currently used in Sustainable Forest Management Plans (SFMPs).

The advancement of mechanization in forestry has increased productivity in the forestry sector, bringing positive and negative impacts that require a deeper understanding for sustainable forest management. This study aimed to apply a simplified instrument for assessing damage and environmental impacts in forest harvesting of commercial eucalyptus plantations, using a combination of methodologies. The methodology used combined interaction networks and impact assessment matrices, carrying out field surveys, transposing them to interaction networks and weighting them through assessment matrices, resulting in environmental indices (ES) for prioritizing actions. The study was conducted on a commercial eucalyptus plantation in the municipality of São Pedro, São Paulo, Brazil. The mechanized harvesting of the area consists of the structure of a module with a mobile unit consisting of a harvester and forwarder. The results indicated that wood transport presented the highest ES, both positive and negative. The most significant negative impacts (ES) were the depletion of water resources and erosion, while the positive impacts included regional development and job creation. The most notable changes, positive and negative, were observed in the physical and anthropic environment, with a lesser impact on the biotic environment.

Polarimetric Synthetic Aperture Radar (PolSAR) images with dual polarization modes have great potential to map FSV by excellent penetration capabilities and distinct microwave scattering processes. However, the response of these SAR data to FSV is still uncertain at non-growing season. To further interpret the response of forest FSV to these dual-polarization SAR images, three types of dual polarization SAR images (GF-3, Sentinel-1, and ALOS-2) were initially acquired in coniferous planted forest at non-growing season. Then, sensitivity between FSV and all alternative features extracted from each type of SAR images were analyzed to express the difference of bands and polarization modes in deciduous (Larch) and evergreen (Chinese pine) forests. Finally, mapped FSVs using single and combined dual polarization images were derived by optimal feature sets and four machine learning models, respectively. The combined effects were also analyzed to clarify the response of FSV to dual polarization SAR images with bands and polarization modes at non-growing season. The results demonstrated that the difference of backscattering energy from different sensors is significant in Chinese pine forests, and the difference is gradually reduced in Larch forests. it is also implied that polarization mode is more important than penetration capability in mapping forest FSV in deciduous forest at non-growing season. By comparing the accuracy of mapped FSV using single and combined images, combined images have more capability to improve the accuracy and reliability of mapped FSV. Meanwhile, it is also confirmed that compensation effect with bands and polarization modes not only have great potential to delay the saturation phenomenon, but also have capability to reduce errors caused by over-estimation.

Visual data on the geographic distribution of carbon storage helps policy maker to formulate countermeasures on global warming. However, Taiwan, as an island showing diversity in climate and topography, had lacked valid visual data in distribution of forest carbon storage between the last to forest surveys (1993-2015). This study established a model to achieve an estimation that capable to demonstrate the distribution of forest carbon storage. This model uses land use, stand morphology, carbon conversion coefficient databases accordingly for 51 types of major forest in Taiwan. An estimation on 2006 was conducted and shows an overall carbon storage of 165.65 Mt C, with forest carbon storage per unit area of 71.56 t C ha–1, where natural forests and plantations respectively contributed of 114.15 Mt C (68.9%) and 51.50 Mt C (31.1%). By assuming no change in land use type, the carbon sequestration from 2006 to 2007 by the 51 forest types was estimated to be 5.21 Mt C yr–1 using historical tree growth and mortality rates. The result reflects the reality of the land use status and event of coverage shifting with time by combining to the two forest surveys in Taiwan.

Growth models of uneven-aged forests on the diameter class level can support silvicultural decision making. Machine learning brings added value to the modeling of dynamics at the stand or individual tree level based on data from permanent plots. The objective of this study is to explore the potential of machine learning for modeling growth dynamics in uneven-aged forests at the diameter class level based on inventory data from practice. Two main modeling approaches are conducted and compared: i) fine-tuned linear models differentiated per diameter class, ii) an artificial neural network (multilayer perceptron) trained on all diameter classes. The models are trained on the inventory data of the Canton of Neuchâtel (Switzerland), which are area-wide data without individual tree-level growth monitoring. Both approaches produce convincing results for predicting future diameter distributions. The linear models perform better at the individual diameter class level with test R2 typically between 50 and 70% for predicting increments in the numbers of stems at the diameter class level. From a methodological perspective, the multilayer perceptron implementation is much simpler than the fine-tuning of linear models. The linear models developed in this study achieve sufficient performance for practical decision support.

High PM10 concentrations are still a significant problem in many parts of the world. In many countries, including Poland, 50μg/m3 is the permissible threshold for a daily averaged PM10 concentration. The number of people affected by this threshold’s exceedance is challenging to estimate and requires high-resolution concentration maps. This paper presents an application of random forests for downscaling regional model air quality results. As policymakers and other end users are eager to receive a detailed resolution PM10 concentration maps, we propose a technique which utilizes the results of regional CTM (GEM-AQ, with 2.5km resolution) and local Gaussian plume model. As a result, we receive a detailed, 250-meter resolution PM10 distribution, which resembles the complex emission pattern in a foothill area in southern Poland. The random forest results are highly consistent with the GEM-AQ and observed concentration. We also discuss different strategies of data training random forest - using additional features and selecting target variables.

Stroke constitutes a significant public health concern due to its impact on mortality and morbidity. This study investigates the utility of machine learning algorithms in predicting stroke and identifying key risk factors using data from the Suita study, comprising 7,389 participants and 53 variables. Initially, unsupervised K-prototype clustering categorized participants into risk clusters, while five supervised models including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosted Machine (Light-GBM) were employed to predict stroke outcomes. Stroke incidence disparities among identified risk clusters using the unsupervised K-prototype clustering method are substantial, according to the findings. Supervised learning, particularly RF was a preferable option because of the higher levels of performance metrics. The Shapley Additive Explanations (SHAP) method identified age, systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood glucose level as key predictors of stroke, aligning with findings from the unsupervised clustering approach in high-risk groups. Additionally, previously unidentified risk factors such as elbow joint thickness, fructosamine, hemoglobin, and calcium level demonstrate potential for stroke prediction. In conclusion, machine learning facilitated accurate stroke risk predictions and highlighted potential biomarkers, offering a data-driven framework for risk assessment and biomarker discovery.

The adoption of sustainable forest management practices emerged as a contemporary imperative for forest biodiversity preservation, functional integrity, and mitigation of climate change. Within the spectrum of these practices, thinning is recognized as an environmentally sustainable strategy. The primary objective of thinning is the equitable redistribution of aboveground growth, diverting resources from younger trees to promote the accelerated development of more valuable specimens compared to unthinned forests. Thinning, while fostering aboveground changes, induces substantial alterations in soil chemical and biochemical properties. This review addresses the often-debated consequences of thinning on soil characteristics, focusing on the intricate interplay involving different thinning intensities and their impact on soil chemical and biochemical parameters. Specifically, the analysis delves into the modulation of organic carbon levels, microbial biomass, and enzymes crucial to the organic matter cycle. Two key aspects are scrutinized: firstly, the influence of thinning intensity and the temporal dimension post-thinning on soil properties; secondly, the comparative impact of thinning intensity versus the time elapsed from the thinning event on soil properties and associated biological processes. The findings underscore pivotal insights: a) temporal dynamics significantly affect soil organic matter across broadleaved (excluding beech), coniferous, and mixed forests, manifesting as early as 2-7 years post-thinning; b) thinning intensity, up to a threshold of 50%, enhances soil quality by augmenting organic carbon content, bolstering microbial communities, and amplifying associated enzyme activities. This review consolidates valuable information for forest managers, providing guidance to optimize natural processes in tandem with achieving specific management objectives. By illuminating the nuanced interactions between thinning practices and soil dynamics, this knowledge equips stakeholders to make informed decisions in the pursuit of sustainable forest management and ecological resilience.

The European heatwave of 2018 led to record-breaking temperatures and extremely dry conditions in many parts of the continent resulting in widespread decrease in agricultural yield, early tree-leaf senescence, and increase in forest fires in Northern Europe. Our study aims to capture the impact of the 2018 European heatwave on terrestrial ecosystem through the lens of a high-resolution solar-induced fluorescence (SIF) data acquired from the Orbiting Carbon Observatory (OCO-2) satellite. SIF is proposed to be a direct proxy for gross primary productivity (GPP) and thus can be used to draw inferences about changes in photosynthetic activity in vegetation due to extreme events. We explore spatial and temporal SIF variation and anomaly during spring and summer months across different vegetation types (agriculture, broadleaved forest, coniferous forest, and mixed forest) during the European heatwave of 2018 and compare it to non-drought conditions (most of Southern Europe). About one-third of Europe’s land area experienced a consecutive spring and summer drought in 2018. Comparing 2018 to mean (2015-2017) conditions, we found a change in intra-spring season SIF dynamics for all vegetation types, with lower SIF during the start of spring followed by an increase in fluorescence from mid-April. Summer, however, showed a significant decrease in SIF. Our results show that particularly agricultural areas were severely affected by the hotter drought of 2018. Furthermore, the intense heat wave in Central Europe showed about 31% decrease in SIF values during July and August as compared to the mean over three previous years. Furthermore, our MODIS and OCO-2 comparative results indicate that especially for forests, OCO-2 SIF has a quicker response and possible higher sensitivity to drought in comparison to MODIS’s fPAR and NDVI when considering shorter reference periods, which highlights the added value of remotely sensed solar-induced fluorescence for studying the impact of drought on vegetation.

In Africa, 80% of households in urban areas are food insecure and is coupled with a dramatically changing urban food culture towards increased consumption of sugary and fatty foods. Consequently, incidences of obesity and undernourishment in many African cities are becoming escalating. Urban and peri-urban forestry emerges as a complementary measure to contribute towards elimination of urban hunger and improved nutritional security. However, there is scanty knowledge about the composition, diversity and socioeconomic contributions of urban food trees in African cities and this hinders policy discussions integrating urban forestry into the food security discourse. This paper examines the diversity and composition of the urban forest and food trees of Accra and sheds light on perceptions of urbanites regarding food tree cultivation and availability in the city. Using a mixed methods approach, about 105 respondents in six neighbourhoods of Accra were interviewed while over 200 100-m2 plots were surveyed across five land use types. Twenty-two out of the 70 woody species in Accra are edible. The food tree abundance in the city is about half of the total number of trees enumerated. The species richness and abundance of the edible trees and all trees in the city were significantly different among land use types (p<0.0001) and neighbourhood types (p<0.0001). The diversity of food bearing tree species was much higher in the poorer neighbourhoods than in the wealthier neighbourhoods. Respondents in wealthier neighbourhoods indicated that tree and fruit tree cover of the city was generally low and showed greater interests in cultivating fruit trees and expanding urban forest cover than poorer neighbourhoods. These findings demonstrate the need for urban food policy reforms that integrate urban grown tree foods in the urban food system/culture.

Background: Diabetes is among the most prevalent diseases worldwide, of all the affected individuals a significant proportion of the population remains undiagnosed because of a lack of specific symptoms early in this disorder and inadequate diagnostics. Diabetes and its associated sequela, i.e., comorbidity are associated with microvascular and macrovascular complications. As diabetes is characterized by an altered metabolism of key metabolites and regulatory pathways. Metabolic phenotyping can provide us with a better understanding of the unique set of regulatory perturbations that predispose to diabetes and its associated comorbidities. Methodology: The present study utilizes the analytical platform NMR spectroscopy coupled with Random Forest statistical analysis to identify the discriminatory metabolites of diabetes (DB) and diabetes-related comorbidity (DC) along with the healthy control (HC) subjects. A combined and pairwise analysis was performed, between the serum samples of HC (n=50), and DB (n=38), and DC (n=35) individuals to identify the discriminatory metabolites responsible for class separation. The perturbed metabolites were further rigorously validated using t-test, AUROC analysis to examine the statistical significance of the identified metabolites. Results: The DB and DC patients were well discriminated from HC. However, 15 metabolites were found to be significantly perturbed in DC patients compared to DB, the identified panel of metabolites are TCA cycle (succinate, citrate), methylamine metabolism (trimethylamine, methylamine, betaine), -intermediates; energy metabolites (glucose, lactate, pyruvate); and amino acids (valine, arginine, glutamate, methionine, proline and threonine). The metabolites were further used to identify the perturbed metabolic pathway and correlation of metabolites in DC patients. Conclusion: The 1H NMR metabolomics may prove a promising technique to differentiate and predict diabetes and its comorbidities on their onset or progression by determining the altered levels of the metabolites in serum.

The current communication presents the application of a consolidated model combination strategy to analyze the medium-term carbon fluxes in two Mediterranean pine wood ecosystems. The modelling strategy is based on the use of a NDVI-driven parametric model, Modified C-Fix, and of a bio-geochemical model, BIOME-BGC, the outputs of which are combined taking into account the actual development phase of each ecosystem. The two pine ecosystems examined correspond to an old-growth forest and to a secondary succession after clearcuts, which differently respond to the same climatic condition during a ten-year period (2013-2022). Increasing dryness, in fact, exerts a fundamental role in controlling the gross primary and net ecosystem production of the mature stand, while the effect of forest regeneration is prevalent for the uprising of the same variables in the other stand. In particular, the simulated net carbon exchange fluctuates around 200 g C m-2 year-1 in the first stand and rises to over 600 g C m-2 year-1 in the second stand; correspondingly, the accumulation of new biomass is nearly undetectable in the former case while becomes notable in the latter. The study therefore supports the potential of the applied strategy for predicting the forest carbon balances consequent on diversified natural and human-induced factors.

Honey has been employed for the treatment of wounds and diseases for ancient time, thanks to its antimicrobial and curative properties. This study aims to present the biochemical characteristics, including the amount of sugar, total phenols, phenolic chemicals, antioxidant properties, and antibacterial activities of a specific type of French honey (Sologne summer forest) in comparison with a manuka honey. According to our findings, the Manuka honey tested has 23% fewer polyphenols total than Sologne summer forest honey. The results showed that the Sologne summer honey had a different polyphenols profile than Manuka honey with specific polyphenol like p- Hydroxybenzoic acid. Additionally, the antioxidant activity of the two honeys is comparable (9 μmole Trolox.g-1 honey). Furthermore, the antibacterial activity of the two honeys is comparable against Pseudomonas aeruginosa and Staphylococcus aureus. Our research indicates for the first time that there are significant nutritional and biological potentials for a French honey from the Sologne summer forest.

Affem Boussou community forest (AFC) abounds in important biological resources. This study, which contributes to its better management, examines the spatiotemporal dynamics of the vegetation and its ecological and structural characteristics to propose a zoning plan for the said forest. The analysis of the spatiotemporal dynamics of land use in the AFC from Google Earth images of 2015, 2018, and 2021 revealed a regressive trend of formations: crops and fallows (-33.98%), dense dry forests (-7.92%), gallery forests (-3.46%), plantations (-100%), grassy savannahs and meadows (-18.84%) except for tree/shrub savannahs (484.23%). The floristic inventory identified 163 species divided into 129 genera and 55 families. Fabaceae (14.02%), and Combretaceae (10.55%) are the most represented families. Anogeissus leiocarpa (5.19%) and Vitellaria paradoxa (4.72%) are the most frequent species. We note the dominance of individuals of small diameters. The regeneration potential of the AFC is 64 feet/ha due to 21 feet/ha of suckers, 29 feet/ha of seedlings, and 14 feet/ha of shoots. As a zoning plan, the AFC was subdivided into four series: the agroforestry zone (18.80%), the sustainable production forest zone (42.22%), the buffer zone (11%), and the biological conservation zone (28%). These results constitute a scientific basis for testing ecological indicators of sustainable management of community forests in Togo.

Accurate fire severity mapping is essential for understanding the impacts of wildfires on vegetation dynamics in arid savannas. The frequent wildfires in these biomes often cause topkill, where vegetation experiences above-ground combustion, but the below-ground root structures survive, allowing for subsequent regrowth post-burn. Investigating post-fire regrowth is crucial for maintaining ecological balance, elucidating fire regimes, and enhancing the knowledge base of land managers regarding vegetation response. This study examined the relationship between bush fire severity and post-burn coppicing/regeneration events of woody vegetation in the Kalahari Desert of Botswana. Utilizing UAV-derived RGB imagery combined with a Random Forest (RF) classification algorithm, we aimed to enhance the precision of burn severity mapping at a fine spatial resolution. Our research focused on a 1 km2 plot within the Modisa Wildlife Reserve, extensively burnt by the Kgalagadi Transfrontier Fire of 2021. The UAV imagery, captured at various intervals post-burn, provided detailed orthomosaics and canopy height models, facilitating precise land cover classification and burn severity assessment. The RF model achieved an overall accuracy of 79.5% and effectively identified key burn severity indicators, including green vegetation, charred grass, and ash deposits. Our analysis revealed a &gt;50% probability of woody vegetation regrowth in high severity burn areas six months post-burn, highlighting the resilience of these ecosystems. This study demonstrates the efficacy of low-cost UAV photogrammetry for fine scale burn severity assessment and provides valuable insights into post-fire vegetation recovery, thereby aiding land management and conservation efforts in savannas.

Acacia dealbata Link, named Mimosa in Portugal, is an invasive hardwood species with potential for construction use, but research is limited. The available stock of small-diameter juvenile wood (sjw) logs can help reduce this gap, but tangential cracking at log ends challenges fastener connections. This study evaluated different treatments to control and reduce end-face cracking in sjw logs during air drying, an economical and environmentally friendly procedure. Extreme two-thirds of sixteen Mimosa logs were subjected to two treatments: one with longitudinal kerfs 15 mm deep along the length (2 and 3 kerfs) and the other with a hollow in the centre up to half the length (16 mm and 30 mm diameters). Over 219 days of air drying and compared with the central part, kerfing treatments significantly reduced outer wood tangential cracking (p &lt; 0.001), with the 3-kerf also reducing crack numbers (p &lt; 0.05) but increasing significantly cracks near the pith (p &lt; 0.01). The 30 mm central hollow significantly reduced central perforation cracking (p &lt; 0.05). Results suggest that a combined treatment approach could help mitigate cracking, enhancing the suitability of wild Mimosa logs for construction use.

The amino acid composition of the active site in an enzyme is influential on its substrate selectivity. For CYP2E1, the role of PHE residues in the formation of effective orientations for its activity toward aromatic substrates remains unclear. In this study, molecular docking and molecular dynamics analysis were performed toward the interactions between PHEs in the active site of human CYP2E1 and various aromatic compounds as confirmed CYP2E1 substrates. The results indicated that the orientation of 1-methylpyrene (1-MP) in the active site was highly modulated by the PHEs, PHE478 contributing to the binding free energy most significantly. Furthermore, by building a random forest model the relationship between each of 19 molecular descriptors of PCB congeners (from molecular docking, quantum mechanics, and physicochemical properties) and established human CYP2E1-dependent mutagenicity of a series of polychlorinated biphenyls (PCBs), which have been proven to be human carcinogens and endocrinal disrupters, was investigated. The presence of PHEs did not appear to significantly modify the electronic or structural feature of each bound ligand (PCB), instead, the flexibility of the molecular conformation of PHEs contributed substantially to the effective binding energy and orientation. It is supposed that PHE residues adjust their own conformation to permit a suitable space for the ligand binding and form an orientation favorable for a biochemical reaction. This study has provided some insights into the role of PHEs in guiding the interactive adaptation of the active site of human CYP2E1 for the binding and metabolism of aromatic substrates.

As time progresses and technology improves, biological data sets are continuously increasing in size. New methods and new implementations of existing methods are needed to keep pace with this increase. In this paper, we present a high performance computing(HPC)-capable implementation of Iterative Random Forest (iRF). This new implementation enables the explainable-AI eQTL analysis of SNP sets with over a million SNPs. Using this implementation we also present a new method, iRF Leave One Out Prediction (iRF-LOOP), for the creation of Predictive Expression Networks on the order of 40,000 genes or more. We compare the new implementation of iRF with the previous R version and analyze its time to completion on two of the world's fastest supercomputers Summit and Titan. We also show iRF-LOOP's ability to capture biologically significant results when creating Predictive Expression Networks. This new implementation of iRF will enable the analysis of biological data sets at scales that were previously not possible.

Forest community connections are crucial to ensure forest stewardship and sustainability. We explored the potential of mushrooming to enable such connections in contexts where these connections have been historically broken, alienating local people from forests. Taking the case of the recent devolution of a community forest (baldios) in central Portugal to the local population, we present a five-year pilot project to rework mycology from a mushroom-centered approach to a mushroom-in-baldios approach. Mushrooms were used as an entry-point to connect the forest ecology with the challenges of governance and community building. The devised activities provided an opportunity for people inside and outside the local community to adventure into the woods and find out more about their socio-ecological history, develop communal and convivial relationships and engage in the responsible gathering of wild mushrooms. However, the hosting of mushroomers to know, value and engage with the community forest recovery has constantly working against the enclosure of mushrooms to provide marketable forms of leisure. The outcome of these activities depends on the relationships established between mushrooms, mycologists, local administrators, commoners and poachers, all operating within a framework that favors the eradication of resources instead of long-term relationships that sustain places.

Nitrogen is one of the most important macronutrients for crops, and in conjunction with artificial intelligence algorithms, it is possible to estimate it with the aid of vegetation indices through remote sensing. Various indices were calculated and those with a correlation ≥ 0.7 were selected for subsequent use in Random Forest, Gradient Boosting, and Artificial Neural Networks to determine their relationship with nitrogen levels measured in the laboratory. Random Forest showed no relationship, yielding an R2 of zero, whereas Artificial Neural Networks yielded the best results with an R2 of 0.93. Thus, it is reliable to estimate nitrogen levels using this algorithm by feeding it with data from TCARI, MCARI, TCARI/OSAVI, and MCARI/OSAVI, assisted by technological tools.

In this report, we present a study demonstrating how machine learning methods can reveal the interaction of different risk factors of post-transplant leukemic relapse and obtain robust predictions even with a modest clinical dataset. Using a cohort of 63 pediatric patients with acute lymphocytic leukemia (ALL) and 46 patients with acute myeloid leukemia (AML) who underwent stem cell transplant at a single institution, we built predictive models of leukemic relapse with both pretransplant and posttransplant patient variables (specifically lineage-specific chimerism) using the random forest classifier. The random forest classifier revealed different important predictive factors between ALL and AML in our relapse models consistent with previous knowledge. Furthermore, it also distinguished donor CD34 chimerism as most impactful in relapse prediction compare to donor chimerism of other cellular lineages in our dataset for ALL but CD3 for AML. Our models greatly improved sensitivity and specificity at predicting relapses in cross validation compared to a reference model based on our own institutional incidence of relapse and inferential statistical principles. Local Interpretable Model-Agnostic Explanations, an interpretable machine learning tool, confirmed our Random Forest Classification result and provided an intuitive explanation of how our machine learning models made the relapse prediction for each individual patient.

Soil enzyme activity can be affected by both production and degradation, as enzymes can be degraded by proteases. However, the impact of nutrient addition on enzyme activity is often solely attributed to changes in enzyme production without fully considering degradation. Here, we demonstrated that the activities of β-1,4-glucosidase (BG), β-D-cellobiohydrolase (CBH), β-1,4-Xylosidase (BX), and β-1,4-N-acetyl-glucosaminnidase (NAG) were comparable in nitrogen (N) and phosphorus (P) fertilized soils and the unfertilized control under field conditions, but the reduction in activity was substantially greater in the fertilized soils during short-term laboratory incubation. The results show that the interruption of the natural, continuous supply of organic matter or non-soil microbial-derived enzymes, which typically occurs under field conditions, leads to a more significant reduction in apparent enzyme activities in fertilized soils compared to unfertilized control. This may be attributed to the higher abundance of protease in fertilized soils, resulting in faster enzyme degradation. Interestingly, P fertilization alone did not have a similar effect, indicating that N fertilization is likely the main cause of the larger decreases in enzyme activity during incubation in fertilized soils compared to unfertilized control soils, despite our study site being poor in P and rich in N. These findings highlight the importance of considering enzyme degradation when investigating material dynamics in forest ecosystems, including the impact of nutrient addition on enzyme activity, as enzyme production alone may not fully explain changes in apparent enzyme activity.

Quaking aspen (Populus tremuloides Michx.) is an important deciduous species in western U.S. forests. Existing maps of aspen distribution are based on Landsat imagery and often miss small stands (&lt;0.09 ha or 30 m²), which rapidly regrow when managed or following disturbance. In this study, we present methods for deriving a new regional map of aspen forests using one year of Sentinel-1 (S1) and Sentinel-2 (S2) imagery in Google Earth Engine. We assessed the annual phenology of aspen in the Southern Rockies and leveraged the frequent temporal resolution of S1 and S2 to create ecologically relevant seasonal composites. Additionally, we derived spectral indices and radar textural features targeting the canopy structure, moisture, and chlorophyll content. Using spatial block cross-validation and Random Forests, we assessed the accuracy of different scenarios and selected the best performing set of features for classification. Comparisons were then made with existing landcover products across the study region. The resulting map improves on existing landcover products in both accuracy (average F1-score = 93.1%) and detection of smaller forest patches. These methods enable accurate mapping at spatial and temporal scales relevant to forest management for one of the most widely distributed tree species in North America.

Cameroon territory is experiencing significant land use and land cover (LULC) changes since its independence in 1960. But the main relevant impacts are recorded since 1990 due to intensification of agricultural activities and urbanization. LULC effects and dynamics vary from one region to another according to the type of vegetation cover and activities. Using remote sensing, GIS and subsidiary data, this paper attempted to model the land use and land cover (LULC) change in the Centre Region of Cameroon that host Yaoundé metropolis. The rapid expansion of the city of Yaoundé drives to the land conversion with farmland intensification and forest depletion accelerating the rate at which land use and land cover (LULC) transformations take place. This study aims at assessing the impacts of both agriculture and urbanization on the LULC change in the Centre Region of Cameroon. A detailed LULC map from MAPBOX high resolution images and three LULC maps were produced from Landsat TM-OLI images (1984-2015). A maximum likelihood classification techniques using ERDAS Imagine, showed forest decline with a total loss of 54% in thirty years. Also, Landsat and MAPBOX images to which we added 1951 aerial photograph and SPOT 6 (2006) were used to analyse urban growth in the city of Yaoundé. The results show a remarkable urban spatial spread of the metropolis between 1951 and 2015, with a peak in 2000. Images processing enabled us to analyse the long term dynamics of LULC change since the 1950s in this Region using ArcGIS & QGIS software’s. Based on this dynamic, a LULC projection map was produced using Markov model on IDRISI Selva, demonstrating the decrease of the dense forest (45% in 2015 to 0.25% in 2050). It was estimated that by 2050, the entire dense forest can be depleted if nothing is done, while only 12.67% of the secondary forest would remain in the Region. Such a projected map is very useful to decision makers for council development and urban planning. This effective forest depletion ties with the hypothesis that urbanization of Yaoundé and its secondary surrounding satellite cities (within a radius of 30-100km) is a veritable driving force of deforestation.

Machine learning plays a key role in present day crime detection, analysis and prediction. The goal of this work is to propose methods for predicting crimes classified into different categories of severity. We implemented visualization and analysis of crime data statistics in recent years in the city of Boston. We then carried out a comparative study between two supervised learning algorithms, which are decision tree and random forest based on the accuracy and processing time of the models to make predictions using geographical and temporal information provided by splitting the data into training and test sets. The result shows that random forest as expected gives a better result by 1.54% more accuracy in comparison to decision tree, although this comes at a cost of at least 4.37 times the time consumed in processing. The study opens doors to application of similar supervised methods in crime data analytics and other fields of data science

Forests, as a form of natural resource, play a significant role in the social, ecological, and economic aspects of community life. One of the communities that live in the forest and dependent on the forest is Orang Rimba in Jambi. The objectives of this research are to investigate changes in ownership and access systems of natural resources within the Orang Rimba community, the factors driving these changes, and the impacts of changes in access and control over natural resources on the socio-cultural conditions of the Orang Rimba community. This research was conducted using a qualitative approach. The result of this research shows that the Orang Rimba community has experienced changes in access and control of forest resources. Many factors contribute to these changes, mainly from the Government and market forces. Moreover, these changes bring about some fundamental changes in Orang Rimba’s livelihood and even their live in general.

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses (NSSRN) dataset and predict nurse turnover using machine learning (ML) algorithms. Four ML algorithms, namely logistic regression (LR), random forests (RF), decision tree (DT), and extreme gradient boosting (XGBoost), are applied to the SMOTE-enhanced dataset. The data is randomly split into an 80% training set and a 20% validation set. Eighteen carefully selected variables from the NSSRN database serve as predictive features, and the machine learning model identifies feature importance concerning nurse turnover. The study includes a performance comparison based on metrics such as Accuracy, Precision, Recall (Sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests (SMOTE_RT) exhibit the most robust predictive power, both in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). XGBoost, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, EHR/EMR usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable ML algorithms for nurse turnover prediction.

CO2 flooding stands as a pivotal technique for significantly enhancing oil recovery in low-permeability reservoirs. The movement and sweeping rules at the front of CO2 flooding play a critical role in its oil recovery, yet a comprehensive quantitative analysis remains an area in need of refinement. In this study, we have developed 1D and 2D numerical simulation models to explore the sweeping behavior of miscible, immiscible, and partly-miscible CO2 flooding patterns. The front position and movement rules of the three CO2 flooding patterns are determined. A novel approach of the contour area calculation method is introduced to quantitatively characterize the sweep coefficients, and the sweeping rules are discussed regarding geological parameters, oil viscosity, and injection-production parameters. Furthermore, the Random Forest (RF) algorithm is employed to identify the controlling factor of the sweep coefficient, as determined by out-of-bag (OOB) data displacement analysis. The results show that the miscible front is located at the point of maximum CO2 content in the oil phase. The immiscible front occurs at the point of maximum interfacial tension near the production well. Remarkably, the immiscible front moves at a faster rate compared to the miscible front. Geological parameters, including porosity, permeability, and reservoir thickness, significantly impact the gravity segregation effect, thereby influencing the CO2 sweep coefficient. Immiscible flooding exhibits the highest degree of gravity segregation, with a maximum gravity segregation degree (GSD) reaching 78.1. The permeability ratio is a crucial factor, with a lower limit of approximately 5.0 for reservoirs suitable for CO2 flooding. Injection-production parameters also play a pivotal role in sweep coefficient. Decreased well spacing and increased gas injection rates are found to enhance sweep coefficients by suppressing gravity segregation. Additionally, higher gas injection rates can improve the miscibility degree of partly-miscible flooding from 0.69 to 1.0. Oil viscosity proves to be a significant factor influencing the sweep coefficients, with high seepage resistance due to increasing oil viscosity dominating the miscible and partly-miscible flooding patterns. Conversely, gravity segregation primarily governs the sweep coefficient in immiscible flooding. In terms of controlling factors, the permeability ratio emerges as a paramount influence, with a factor importance value (FI) reaching 1.04. these results provide a theoretical foundation for the application of CO2 flooding, enhancing the understanding of the critical factors governing its success.

Cervical Cancer affects a large part of female population that makes the prediction of this disease based on Machine Learning (ML) by outmost importance. ML algorithms can be integrated in complex intelligent agent-based systems that can offer decision support to the resident medical doctors or even to experienced medical doctors. For instance can be mentioned the situation when an experienced medical doctor diagnose a case but he/she needs expertise support that is related to another medical specialty. Data imbalance is frequent in healthcare data and has a negative influencing effect in making predictions using ML algorithms. Cancer data generally and cervical cancer data particularly are frequently imbalanced. Based on this fact the study of data imbalance impact on diverse state-of-the-art ML prediction algorithms is important. This research subject is also motivated by the fact that in many research are presented experimental evaluations of algorithms without characterization of the data on that they have been applied. Such characterizations could give clear indication to other researchers regarding the applicability of the algorithms on their specific data. Specifically, if the data have the respective characteristics than are expectable the same performance evaluation results like those in the reported research. For the study we chosed a messy real-life Cervical Cancer dataset available in a recognized data repository included a large amount of missing and noisy values. To identify the best imbalanced technique for this medical dataset, it is compared the performance of eleven important resampling methods combined with the following state-of-the-art ML models: K-Nearest Neighbours (with k values of 2 and 3), binary Logistic Regression, and Random Forest, that are frequently applied in prediction types of researches in healthcare. The studied resampling methods includes seven undersampling methods namely Condensed Nearest Neighbour, Tomek Links, Edited Nearest Neighbours, Repeated Edited Nearest Neighbours, All K-Nearest Neighbours, NearMiss, Neighbourhood Cleaning Rule, and Instance Hardness Threshold, and four oversampling methods namely Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling Approach for Imbalanced Learning SMOTE, Support Vector Machine SMOTE and Borderline SMOTE. In the case of the dataset for the confidence interval with 95% confidence level was between 9.23 and 16.22, while the imbalance ratio is 12.73. The obtained results show that resampling methods help the learning models to improve the classification ability of cervical cancer. The applied oversampling techniques generally showed better results than undersampling methods. In the case of Logistic Regression classifier had the highest impact on balanced techniques, while Random Forest had promising performance, even before balancing techniques and KNN2 was generally better than KNN3.

One of the main products of the forest, which has the greatest economic impact, is wood. Due to its characteristics, the wood requires certain types of vehicles for transport it. For this reason, the accessibility of the stands with forest roads plays significant role in the efficiency of the wood logging process, which aims to bring the wood from the forest to the harvesting area located, frequently, next to a permanent transport route. The process of wood transport from the forest initially takes place on forest roads and after that on public roads. The technological process of wood transport represents an important stage in this process, and its good organization can have implications on the final price of the wood material. Based on those mentioned above, the paper aims to highlight the factors that can influence productivity in the case of loading wood in forestry trucks and forestry platforms, in different conditions. Thus, the research was carried out in four counties in Romania and addressed the loading of wood in different forestry trucks and platforms, with or without trailers. Following the evaluation of the work phases specific to the process of round wood loading in vehicles of transport, it was found that sometimes a significant importance is given to the working phases that can be carried out before the loading process, as phases of preparation of the wooden material in order to load it. Also, the facilities of the transport vehicles, the assortments of wood material, as well as the experience of the operators are the main factors that can lead to an increase in productivity.

Remote sensing/GIS techniques are a versatile tool for x-raying serial forest structural changes in retrospect. It would be impossible to evaluate past occurrences and changes in forest extents in past decades at Effan Forest Reserve without non-conventional means. Therefore, we adopted remote sensing technology using Landsat images to evaluate land-use change and degradation rates in the area with a view to ascertaining causal factors for possible minimization of forest degradation in Effan Forest Reserve. Land-use/land-cover changes were analyzed using USGS-Landsat TM and ETM images of 1987, 2002, 2014 and 2019. Field-data were collected using handheld GPS receiver and spatial statistical analyses were conducted using the ground control points (GCPs). For inventory data, a systematic sampling technique was adopted using ten 1.05 km-transects at 500 m intervals. A total of 50 sample plots of 50 × 50 m were used. All tree species with Dbh ≥10 cm were enumerated. Nineteen tree species in ten families were encountered with Vitellaria paradoxa as the most-frequently occurring species in the area. IUCN-listed endangered Pterocarpus erinaceus, hitherto abundant in the area, was rarely encountered during the survey, while Vitellaria paradoxa is gradually shrinking, going the relative abundance in the area. The result further showed that primary and secondary forests decreased considerably by 258.03 ha (46.72%) and 9.18 ha (3.63%), respectively, with a total forest loss of 50.3% in 32 years (8.4 hayr-1, 1.6% per annum). While forest plantation size doubled by 369.72 ha within the period. This is worrisome as the remaining fragmented forests appeared to be on the decline, except the riparian vegetation, due to inaccessibility to the riparian by loggers. It thus appeared that forest protection approaches were ineffective. Increased protection efforts could save this forest reserve, and the concerned authority should consider a focused-enrichment planting involving indigenous species for ecosystem-repair.

This review paper is intended to exhibit the interplays between environmental change and rapid population growth in developing countries. In the course of discussion, the impacts of rapidly population growing on the environment have been discussed, and evidence, from various parts of the world have been traced. Studies on the impacts of population pressure on environment have been critically reviewed. It is revealed that all across the developing countries, farm size is shrinking as farmers continue to subdivide holdings among their children. In countries such as Malawi, Rwanda, Ethiopia, Haiti, Nepal and Bangladesh, population growth rates are high, and the non-farm sector is still in its early stages of development. Demographic pressure, land scarcity, and land fragmentation drive greater rural vulnerability and poverty, marked by decreased food security, inadequate response to such natural disasters such as drought or pest infestations, weakened resilience to shocks, and poor health. It is not just the supply of food, fodder, and fuel wood but the resource base itself and the lives that depend upon it are being affected. The evidences pinpoints that man through his non-sustainable production and consumption patterns, is placed at the heart of environmental changes. However, contradictory view, and practices are also in place that the population growth has positive impacts environmental restoration and improvements, while other evidences show insignificant effect of population on the environment. This contradicting scenario puts scholars in argument, and still need further research. Hence, it would be a blind generalization to draw conclusion from this relationship alone, rather, another factor that acts beyond population pressure must also be considered to justify the impact of population on environmental changes.

With cities experiencing faster warming rates than their surroundings and two-thirds of the global population projected to be living in urban areas by 2050, studies that help to describe in detail the spatial temperature patterns in the urban environment have the potential to address concerns regarding cities’ livability. The goal of this research was to examine the spatial pattern of temperature across multiple small to medium-sized cities in the state of Iowa, a relatively rural state. The study utilized mobile temperature sensors to collect air temperature data at a high temporal and spatial resolution in ten urban areas in Iowa during the afternoon, evening, and night on days exceeding 32°C from June to September 2022. Using a Random forest algorithm, and independent variables derived from aerial imagery and LiDAR data, we created predicted surface temperature models that demonstrated R² coefficients ranging from 0.879 to 0.997 with a majority of the temperature models reaching a R² higher than 0.95. These strong modeling results and derived highly detailed raster spatial data supports recent research which help explain the influence of morphometric features on temperature patterns in the urban environment. This study expands on previous research by investigating multiple small to medium sized cities in Iowa.

China historically exhibits spatial differentiation from population distribution to ecological or economic development, and the forest pest control work is an epitome of this tendency. In recent times, global warming, man-made monoculture tree plantations, increasing human population density and intensified international trade aggravate forest pest outbreaks. Although Chinese government has complied with the internationally recommended practices, few stones remain unturned due to existing differential regional imbalance of forest pest distribution and control abilities. Evidence shows that the high-income provinces in the south have taken advantage of economic and technological superiority, resulting in the adoption of more efficient pest-control measures. To the contrary, in economically underdeveloped provinces of the northwest, a paucity of financial support has led to serious threats of pest damage that almost mirrored the demarcations of the Hu Huanyong Line. In this paper, we propose introducing public-private partnership (PPP) model into forest pest control and combining the national strategies to enact regional prevention measures in order to break the current spatially differentiated trends in China.

This research investigates the exposure of plant species to extreme drought events in the Brazilian Atlantic Forest, employing an extensive dataset collected from 205 automatic weather stations across the region. Meteorological indicators derived from hourly data, encompassing precipitation, maximum and minimum air temperature, were utilized to quantify past, current, and future drought conditions. The dataset, comprising 10,299,236 data points, spans a substantial temporal window and exhibits a modest percentage of missing data. Missing data were excluded from analysis, aligning with the decision to refrain from imputation methods due to potential bias. Drought quantification involved the computation of the Aridity Index, the analysis of consecutive hours without precipitation, and the classification of wet and dry days per month. Mann-Kendall trend analysis was applied to assess trends in evapotranspiration and maximum air temperature, considering their significance. The hazard assessment, incorporating environmental factors influencing tree growth dynamics, facilitated the ranking of meteorological indicators to identify regions most exposed to drought events. The results revealed consistent occurrences of extreme rainfall events, indicated by positive outliers in monthly precipitation values. However, significant trends were observed, including an increase in daily maximum temperature and consecutive hours without precipitation, coupled with a decrease in daily precipitation across the Brazilian Atlantic Forest. No significant correlation between vulnerability ranks and weather station latitudes and elevation were found, suggesting geographical location and elevation does not strongly influence observed dryness trends.

We tested selecting data randomly or proportionally in class imbalanced sample. Collecting data into the training and test set according to the initial ratio of QSOs, galaxies and stars were rec-ommended. We experimented using the original imbalanced data or introducing the class balance technologies: SMOTE, SMOTEENN, SMOTETomek, ADASYN, BorderlineSMOTE1, Border-lineSMOTE2, and RandomUndersampling. The SMOTEENN performed the best in the Sample 1. The LightGBM, CatBoost, XGBoost, and RF were compared when adopting the SMOTEENN using the petroMag_u, petroMag_g, petroMag_r, petroMag_i, petroMag_z, J, H, Ks, W1, W2, W3, W4 magnitudes as features. All of the precisions or recalls exceeded 0.94. The RF cost a little more time than the other three algorithms, but resulted in the best evaluating indicators. Utilizing the SMOTEENN +RF technology, the precision, recall and f1-score for QSOs (galaxies, stars) could achieve 0.98 (0.99, 0.98), 0.99 (0.96, 1.00), 0.98 (0.97, 0.99) respectively in Sample 1. Utilizing the SMOTEENN +RF technology, the precision, recall and f1-score for QSOs (galaxies, stars) could achieve 0.94 (0.96, 0.96), 0.98 (0.90, 0.97), 0.96 (0.93, 0.97) using the petroMag_u, petroMag_g, petroMag_r, petroMag_i, petroMag_z, W1, W2, W3, W4 magnitudes as features.

In tropical Africa, forests and savannas are the two most widespread biomes and potentially represent alternative stable states with divergent species composition. A classic, but untested, hypothesis posited by White (1983) suggests that the transition zones between forests and savannas contain a floristically impoverished assemblage with few representatives from each biome. Further, the evolutionary dimension of diversity has received limited attention, despite its importance for understanding the biogeographic history of biomes. Here, we quantify species richness and several measures of evolutionary diversity in 1° grid cells, using c. 300K occurrence records of trees and shrubs combined with biome affiliation data for 3,125 species. We find that assemblages in transition zones hold fewer woody species than assemblages in forest and savanna zones, as posited by White. However, transition zones hold more phylogenetic diversity than expected given their species richness, whether one considers forest and savanna assemblages separately or together. We also show that the Congo basin forest has low levels of phylogenetic diversity given the number of species and highlight south-eastern African savannas as a centre of savanna woody species richness and phylogenetic diversity. Regions with high phylogenetic diversity given the number of both forest and savanna species were centred around the Dahomey Gap and Cameroon, mainly in transition zones. Overall, our study shows that even if floristically impoverished, transition zones lead to unexpectedly high evolutionary diversity, suggesting they are important centres of evolutionary innovation and diversification.

Ecological corridors function as a viable way to mitigate the environmental impact arising from forest fragmentation by interconnecting forest fragments through various techniques. In this context, the objective of this study is to propose a route for the implementation of an ecological corridor in the Itapemirim river watershed. The specific objectives were: (i) to delimit the permanent preservation areas (APP) of the Itapemirim river watershed and compare land use and land cover in the delimited areas; (ii) to calculate landscape ecology indices and select the forest fragments with the highest potential for ecological corridor implementation using Fuzzy logic; (iii) to assess costs and trace the best route for ecological corridor implementation, considering distance and physical impediments; (iv) to assess land costs and expropriation costs to delimit the ecological corridor in the study area. To map land use and land cover, the MapBiomas platform was used, based on Landsat 8 satellite images. The permanent preservation areas were delimited according to criteria established by Law No. 12.651 of May 25, 2012, which establishes parameters, definitions, and limits for APP. The characterization and structural quantification of some landscape ecology indices were performed using the QGIS 3.26 computational application, through the LecoS 3.0.1 plugin and Fragstats 4.2. The connected forest fragments were the Caparaó National Park, the Serra das Torres State Natural Monument, and the fragments selected through the application of Fuzzy logic to the landscape ecology indices. The corridor was delimited according to the lowest cost route, considering land use and land cover, APP, fragment potential, slope, and subnormal clusters. For each cost raster image, its respective statistical weights were calculated using the Analytic Hierarchy Process (AHP) hierarchical method, as well as for the analysis of priority areas for forest restoration, considering land use and land cover, APP, pedology, lithology, and biological importance. The interconnection between protected areas and fragments with the ecological corridor followed the orientation described by CONAMA nº 09/96. Based on the development of the work, the following results were identified: the highest land use and land cover class is pasture. Of the area designated for permanent preservation, 68.58% is in conflicting use with the legislation. The bare land value per hectare of the pasture class is the second highest among the bare land value per LULC values, representing 64.28% of the total. The priority area map showed that 31.86% of the area was classified as of very high or high importance and 42.97% as low or very low priority for forest restoration. Thus, it is concluded that the least cost path algorithm associated with the result generated by the multi-criteria decision method (AHP) constitutes an important tool for planning and implementing an ecological network by taking into account the primary factors for decision-making regarding the location of the best route.

The purpose of this study was to systematically review forest therapy programs designed to decrease the level of depression among adults and subsequently identify the gaps in the literature. This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The authors independently screened full-text articles from various databases using the following criteria: 1) intervention studies assessing the effects of forest therapy on depression in adults aged 18 years and over; 2) studies including at least one control group or condition; 3) been peer-reviewed; and 4) been published either in English or Korean before July 2016. The Scottish Intercollegiate Guideline Network (SIGN) measurement tool was used to assess the risk of bias in each trial. In the final sample, a total of 28 articles (English: 13, Korean: 15) were included in the present systematic review. This review concluded that forest therapy is one of the emerging and effective interventions for decreasing the level of depression in adults. However, the studies included in this review lacked methodological rigor. Future studies assessing the long-term effect of forest therapy on depression using rigorous study designs are needed.

The Loess Plateau is an important region for vegetation restoration in China, however, changes in soil organic carbon (SOC), soil nutrients, and stoichiometry after restoration in this vulnerable ecoregion are not well understood. Typical restoration types, including orchardland (OL), grassland (GL), shrubland (SL), and forestland (FL) were chosen to examine changes in the stocks and stoichiometry of SOC, soil total nitrogen (TN), and soil total phosphorus (TP) at different soil depths and recovery times. Results showed that SOC stocks first increased and then stabilized in OL, GL, and SL at 0–30 cm depth, while in FL, stocks gradually increased. Soil TN stocks first increased and then decreased in OL, SL, and FL with vegetation age at 0–30 cm depth, while soil TP stocks showed little variation between restoration types. In the later stages of restoration, the stocks of SOC and soil TN at 0–30 cm soil depth were still lower than those in natural grassland (NG) and natural forest (NF). The overall C:N, C:P, and N:P ratios increased with vegetation age. Additionally, the SOC, soil TN and soil TP stocks, and C:N, C:P, and N:P ratios decreased with soil depth. The FL had the highest rate of change in SOC and soil TN stocks, at 0-10 cm soil depth. These results indicate a complex response of SOC, soil TN, and soil TP stocks and stoichiometry to vegetation restoration, which could have important implications for understanding C, N, and P changes and nutrient limitations after vegetation restoration.

Biofertilizer, an environment-friendly and renewable plant nutrient source, has been widely applied and studied to reduce dependency on chemical fertilizers. However, most studies focus on the effects of biofertilizer on the bacterial and fungal communities, and we still lack an understanding of biofertilizer on the protistan community. Here, the effects of biofertilizer application on the composition and interaction of the protistan community in the wheat rhizosphere were investigated based on a 4-year field experiment. Biofertilizer application altered soil physicochemical properties and the protistan community composition (ANOSIM, p &lt; 0.001), and significantly induced an alpha diversity decline. Random forecast and redundancy analysis demonstrated that nitrogenase activity and available phosphorus were the main drivers. Trichomonas classified to the phylum Metamonada was enriched by biofertilizer, and was significantly positive connections with soil nitrogenase activity and some function genes involved in nitrogen-fixation and nitrogen-dissimilation. Biofertilization loosely connected biotic interactions, while did not affect the stability of the protistan community. Besides, biofertilizer promoted the connections of protists with fungi, bacteria, and archaea. Combined with the conjunct biotic network (protist, fungi, bacteria, and archaea) and interactions between protists and soil physicochemical properties/function genes, protists may act as keystone taxa potentially driving soil microbiome composition and function.

Taking a typical forest underlying surface as the research area, this study employed the unmanned aerial vehicle (UAV) photogrammetry to explore more accurate canopy parameters including tree height and canopy radius, which were used to improve the Noah-MP land surface model conducted in Dinghushan Forest Ecosystem Research Station (CN-Din). While the canopy radius was fitted as a Burr distribution, the canopy height of CN-Din forest followed a Weibull distribution. The replacement of the parameters by these observed UAV would result in the Noah-MP model. It was found that the influence on the simulation of the energy fluxes could not be negligible, and the main influence of these canopy parameters was on the latent heat flux which could decrease up to -11% in the midday while increase up to 15% in the nighttime. Additionally, this work indicated that the description of the canopy characteristics for the land surface model should be improved to accurately deliver the heterogeneity for the underlying surface.

Background: The COVID-19 pandemic, caused by the novel coronavirus SARS-CoV-2 has posed unprecedented challenges to healthcare systems worldwide. Here, we have identified proteomic and genetic signatures for improved prognosis which is vital for COVID-19 research. Methods: We investigated the proteomic and genomic profile of COVID-19 positive patients (n=400 for proteomics, n=483 for genomics), focusing on differential regulation between hospitalised and non-hospitalised COVID-19 patients. Signatures had their predictive capabilities tested using independent machine learning models such as Support Vector Machine (SVM), Random Forest (RF) and Logistic Regression (LR). Results: This study has identified 224 differentially expressed proteins in hospitalised COVID-19 patients compared to non-hospitalised COVID-19 patients, involved in various inflammatory and immunological pathways. LGALS9 (p-value < 0.001), LAMP3 (p-value < 0.001), PRSS8 (p-value < 0.001) and AGRN (p-value < 0.001), were identified as the most statistically significant proteins. Several hundred rsIDs were queried across the top 10 significant signatures, identifying three significant SNPs on the FSTL3 gene showing correlation with hospitalisation status. Conclusion: Our study has not only identified key signatures of COVID-19 patients with worsened health but has also demonstrated their predictive capabilities as potential biomarkers, which suggests a staple role in the worsened health effects caused by COVID-19.