Keywords: Wood residuals; Forest biomass; Wood composite; Wood floor; Life Cycle Assessment.

Continuous water resources monitoring is needed for sustainable urban water supply. Remote sensing techniques have proven useful for monitoring some water qualitative parameters with optical characteristics. The study area was the Marateca reservoir in central inland Portugal. The aims were the following: (1) to explore the water quality parameters at the monitoring points of the Marateca reservoir that may explain the event; (2) to validate optical water quality parameters with the monitoring points data; and (3) to model the reservoir water characteristics regarding its deepness, trophic state, and turbidity. The parameters total phosphorus, total nitrogen, and chlorophyll-a were used to compute a trophic level index. The Sentinel-2 imagery was used to compute spectral indices and bands image ratio; to obtain spectral signatures for the monitoring points, and to model water characteristics. The water parameters were above the recommended values at the reservoir entry point from the Ocreza River. The reservoir trophic level was Hypereutrophic and Eutrophic. The spectral signatures confirmed a Hypereutrophic pattern in the entry point. The Marateca reservoir’s water characteristics modeling forecasted problematic zones by contamination. The methodological approach developed can be easily applied to other reservoirs and is a key support tool for decision-makers.

Accurately quantifying the above-ground volume (AGV) and thus above-ground biomass (AGB) of forest stands is an important aspect in the conservation of mangrove ecosystem owing to their ecological and economic benefits. However, the number of studies focusing on quantifying mangrove forests’ biomass has been relatively low due to their marshy terrain, making exploratory studies challenging. In recent times, the use of LiDAR technologies in forest inventory studies has become increasingly popular, due to the reliability of LiDAR as a highly accurate means of 3D spatial data acquisition. In this study, we propose an end-to-end methodology for estimating AGV of mangrove forest stands from terrestrial LiDAR data. Many of the recent studies on this topic effectively employ machine learning algorithms such as multi layer perceptron, random forests, etc. for filtering foliage in the point cloud data of single trees. This study further extends that approach by incorporating the impact of class imbalance of forest point cloud data in a weighted random forest classifier. For the task of segmentation of wood/foliage points in a single tree point cloud, this approach yielded an average increase of 2.737% in the balanced accuracy score, 0.007 in the Cohen’s kappa score, 2.745% in the ROC AUC score and 0.857% in the F1 score. For the task of AGV estimation of a single tree, this approach resulted in an average coefficient of determination of 0.93 with respect to the ground truth volumes. For the task of counting pneumatophores in a plot-level point cloud, the proposed breadth-first searching method yielded an average coefficient of determination of 0.9391. Also, the machine learning classifier and geometric features used in this study were invariant to tree species and hence could be generalised for the classification of point clouds of other tree species as well. Finally, a breadth-first graph-search segmentation based approach is also proposed as part of this pipeline to estimate the contribution of pneumatophores to the AGB of mangrove forest stands. Since pneumatophores are a special adaptation of mangrove forests for gaseous exchange in marshy environments, this study aims to incorporate the detection and AGB estimation of pneumatophores in the inventory of mangrove forest stands. Studying the contribution of pneumatophores to the AGB of mangrove forest plots could also aid future mangrove forest inventory studies in modeling the underlying root network and estimating the below-ground biomass of mangrove trees.

Forest road pavement needs an evaluation methodology based on a comprehensive assessment of road conditions. This research was conducted to evaluate the performance of a method for rating the surface condition of forest roads and eventually to adapt the method to the situation prevailing in a forest road network. The rating method selected as the basis for this experiment was the pavement condition index (PCI) developed by the U.S. Army Corps of Engineers. A 53 km of forest roads were selected contained the most influential factors and conditions variability. Eventually, 201 road segments were delineated between 150-300 m in length. Within the given segments, sample plots were set 20 m in length consecutively. It was concluded that the panel scores for distress and surface condition of sample unit and section differed from forest road pavement condition index (FRPCI) and PCI. Linear regression was used to derive equations between distress and PCI score to determine effective FRPCI parameters that provide a numerical rating for the condition of road segments within the road network, where 0 worlds are the worst possible condition, and 100 is the best possible condition best. Also, regression analysis showed the FRPCI model with a 0.87 correlation for the total of the road is a performance index used for the first time in forest roads. This study showed a range of FRPCI from 7.8 to 96.3, different from PCI and URCI ratings (0.85-45 and 1.2-53). The FRPCI index helps forest managers in road maintenance, harvesting, and planning to use road information.

Crop-type mapping is an important intermediate step for cost-effective crop management at the field level, as an overview of all fields with a particular crop type can be used for monitoring or yield forecasting, for instance. Our study used a data set with 2400 fields and corresponding satellite observations from the federal state of Bavaria, Germany. The study classified corn, winter wheat, winter barley, sugar beet, potato, and winter rapeseed as the main crops grown in Upper Bavaria. We additionally experimented with a rejection class "Other", which summarised further crop types. Corresponding Sentinel-2 data included the normalised difference vegetation index (NDVI) and raw bands from 2016 to 2018 for each selected field. The influence of raw bands compared to NDVI was analysed and the classification algorithms, i.e. support vector machine (SVM) and random forest (RF), were compared. The study showed that the use of an index should be critically questioned and that raw bands provided a wider spectral bandwidth, which significantly improved the mapping of crop types. The results underline the use of RF with raw bands and achieved overall accuracies (OA) of up to 92%. We also predicted crop types in an unknown year with significantly different weather conditions and several months before the end of the growing season. Thus, the influence of climate anomalies and the accuracy depending on the time of prediction were assessed. The crop types of a test site and year without labels could be determined with an OA of up to 86%. The results demonstrate the usefulness of the proof-of-concept and its readiness for use in real applications.

Tropical island countries are often highly populated and deliver immense ecosystem service benefits. As human wellbeing depends on these ecosystems proper management is crucial in the resource-rich tropical lands where related research is less. Though the ecosystem service and biodiversity studies are a promising path to inform the ecosystem management for these mostly developing countries published evidence of using ecosystem service studies in decision-making is lacking. The purpose of this study is to provide an overview of ecosystem services and related research in Sri Lanka examining trends and gaps and how these studies are conceptualized. Out of considered 139 peer-reviewed articles majority of articles 42.4% were terrestrial and forest related while coastal ecosystems were considered in 34.5% of studies. In most studies, the ecosystem service category was provisioning (33.8%) followed by regulatory service (30.9%). Studies investigating and quantifying ecosystem services, pressures on ecosystems, and their management were fewer compared to studies related to biodiversity or species introduction. Moreover, studies investigating the value of ecosystem services and biodiversity to the communities or involvement of stakeholders in the development of management actions regarding the ecosystem services were rare in Sri Lanka and intense focus of future studies in these aspects are timely and necessary.

Monitoring drought impacts in forest ecosystems is a complex process, because forest ecosystems are composed of different species with heterogeneous structural compositions. Even though forest drought status is a key control on the carbon cycle, very few indices exist to monitor and predict forest drought stress. The Forest Drought Indicator (ForDRI) is a new monitoring tool developed by the National Drought Mitigation Center (NDMC) to identify forest drought stress. ForDRI integrates 12 types of data, including satellite, climate, evaporative demand, ground water, and soil moisture, into a single hybrid index to estimate tree stress. The model uses Principal Component Analysis (PCA) to determine the contribution of each input variable based on its covariance in the historical records (2003–2017). A 15-year time series of 780 ForDRI maps at a weekly interval were produced. The ForDRI values at a 12.5km spatial resolution were compared with normalized weekly Bowen ratio data, a biophysically based indicator of stress, from nine AmeriFlux sites. There were strong and significant correlations between Bowen ratio data and ForDRI at sites that had experienced intense drought. In addition, tree ring annual increment data at eight sites in four eastern U.S. national parks were compared with ForDRI values at the corresponding sites. The correlation between ForDRI and tree ring increments at the selected eight sites during the summer season ranged between 0.46 and 0.75. Generally, the correlation between the ForDRI and normalized Bowen ratio or tree ring increment are reasonably good and indicate the usefulness of the ForDRI model for estimating drought stress and providing decision support on forest drought management.

Soil hydraulic properties are often derived indirectly, i.e. computed from easily available soil properties with pedotransfer functions (PTFs), when those are needed for catchment, regional or continental scale applications. When predicted soil hydraulic parameters are used for the modelling of the state and flux of water in soils, uncertainty of the computed values can provide more detailed information when drawing conclusions. The aim of this study was to update the previously published European PTFs (Tóth et al., 2015, euptf v1.4.0) by providing prediction uncertainty calculation built into the transfer functions. The new set of algorithms was derived for point predictions of soil water content at saturation (0 cm matric potential head), field capacity (both -100 and -330 cm matric potential head), wilting point (-15.000 cm matric potential head), plant available water, and saturated hydraulic conductivity, as well as the Mualem-van Genuchten model parameters of the moisture retention and hydraulic conductivity curve. The minimum set of input properties for the prediction is soil depth and sand, silt and clay content. The effect of including additional information like soil organic carbon content, bulk density, calcium carbonate content, pH and cation exchange capacity were extensively analysed. The PTFs were derived adopting the random forest method. The advantage of the new PTFs is that they i) provide information about prediction uncertainty, ii) are significantly more accurate than the euptfv1, iii) can be applied for more predictor variable combinations than the euptfv1, 32 instead of 5, and iv) are now also derived for the prediction of water content at -100 cm matric potential head and plant available water content.

Wildfire susceptibility maps display the wildfires occurrence probability, ranked from low to high, under a given environmental context. Current studies in this field often rely on expert knowledge, including or not statistical models allowing to assess the cause-effect correlation. Machine learning (ML) algorithms can perform very well and be more generalizable thanks to their capability of learning from and make predictions on data. Italy is highly affected by wildfires due to the high heterogeneity of the territory and to the predisposing meteorological conditions. The main objective of the present study is to elaborate a wildfire susceptibility map for Liguria region (Italy) by applying Random Forest, an ensemble ML algorithm based on decision trees. Susceptibility was assessed by evaluating the probability for an area to burn in the future considering where wildfires occurred in the past and which are the geo-environmental factors that favor their spread. Different models were compared, including or not the neighboring vegetation and using an increasing number of folds for the spatial-cross validation. Susceptibility maps for the two fire seasons were finally elaborated and validated and results critically discussed highlighting the capacity of the proposed approach to identify the efficiency of fire fighting activities.

The ASCE-EWRI reference evapotranspiration (ETo) equation is recommended as a standardized method for reference crop ETo estimation. However, various climate data as input variables to the standardized ETo method are considered limiting factors in most cases and restrict the ETo estimation. This paper assessed the potential of different machine learning (ML) models for ETo estimation using limited meteorological data. The ML models used to estimate daily ETo included Gene Expression Programming (GEP), Support Vector Machine (SVM), Multiple Linear Regression (LR), and Random Forest (RF). Three input combinations of daily maximum and minimum temperature (Tmax and Tmin), wind speed (W) with Tmax and Tmin, and solar radiation (Rs) with Tmax and Tmin were considered using meteorological data during 2003–2016 from six weather stations in the Red River Valley. To understand the performance of the applied models with the various combinations, station, and yearly based tests were assessed with local and spatial approaches. Considering the local and spatial approaches analysis, the LR and RF models illustrated the lowest rate of improvement compared to GEP and SVM. The spatial RF and SVM approaches showed the lowest and highest values of the scatter index as 0.333 and 0.457, respectively. As a result, the radiation-based combination and the RF model showed the best performance with higher accuracy for all stations either locally or spatially, and the spatial SVM and GEP illustrated the lowest performance among models and approaches.

Secondary forests (SF) are important carbon sinks, removing CO₂ from the atmosphere through the photosynthesis process and storing photosynthates in their aboveground live biomass (AGB). This process occurring at large-scales partially counteracts C emissions from land-use change, playing, hence, an important role in the global carbon cycle. The absorption rates of carbon in these forests depend on forest physiology, controlled by environmental and climatic conditions as well as on the past land use, which is rarely considered for retrieving AGB from remotely sensed data. In this context, the main goal of this study is to evaluate the potential of full polarimetric ALOS-2 PALSAR-2 data for estimating AGB by taking into account the past-land use of SF areas in the Brazilian Amazon. We surveyed a chronosequence of 42 SF plots (20 ha) near the Tapajós National Forest in Pará state to quantifying AGB growth rates. We explored the full polarimetric data testing three regression models including non-linear (NL), multiple linear regressions models (MLR), and the semi-empirical extended water cloud model (EWCM). The results showed that the intensity of previous use has affected the structure of SF by reducing the AGB accumulation and being noticeable by several polarimetric attributes. The combination of multiple prediction variables with MLR improved the AGB estimation by 70% comparing amongst other models (R² adj. = 0.51; RMSE = 13.2 Mg ha^-1) bias = 2.1 ± 37.9 Mg ha^-1. The error propagation of the MLR model was estimated to be 15%.

In the lowland forests of south-western Poland, the effect of the fencing of forest regeneration stages, aged up to 20 years, upon the level of damage inflicted by red deer (Cervus elaphus), fallow deer (Dama dama), and roe deer (Capreolus capreolus) in non-fenced patches of this age class of forest was studied. In the studied forest districts (n=4), there was the highest proportion of the mixed coniferous‑deciduous forest types, where the main forest‑forming tree species were pine (Pinus sylvertris), birch (Betula sp.), oak (Quercus sp.), beech (Fagus sylvatica), and spruce (Picea abies). At the forest district level, the percentage of fenced areas in young forest plantations (1‑10‑year old) ranged, on average, from 9.1-30.9%, and that in tickets (11-20‑year old) ranged from 0.0%-10.2%. The percentage of areas of severely damaged young plantations fluctuated between 5.7 and 14.2%, and that of tickets fluctuated between 0.3-12.9%. For young plantations, a statistically significant correlation (“r” ranged from 0.51-0.75) was obtained between percentage of area in fenced plots and the level of damage caused by deer. For thickets, this correlation was obtained solely in Pieńsk Forest District (r = 0.646). In the studied forest districts, the fencing of young plantations and thickets resulted in the reduction of average potential food base for cervids, from 2.9 to 10.0 %. An attempt was made to interpret the level of deer damage on the basis of an index, taking into account the standing crop of deciduous browse and forbs, and the population density of cervids.

Today, non-expensive remote sensing (RS) data from different sensors and platforms can be obtained at short intervals and be used for assessing several kinds of forest characteristics at the level of plots, stands and landscapes. Methods such as composite estimation and data assimilation can be used for combining the different sources of information to obtain up-to-date and precise estimates of the characteristics of interest. In composite estimation a standard procedure is to assign weights to the different individual estimates inversely proportional to their variance. However, in case the estimates are correlated, the correlations must be considered in assigning weights or otherwise a composite estimator may be inefficient and its variance be underestimated. In this study we assessed the correlation of plot level estimates of forest characteristics from different RS datasets, between assessments using the same type of sensor as well as across different sensors. The RS data evaluated were SPOT-5 multispectral data, 3D airborne laser scanning data, and TanDEM-X interferometric radar data. Studies were made for plot level mean diameter, mean height, and growing stock volume. All data were acquired from a test site dominated by coniferous forest in southern Sweden. We found that the correlation between plot level estimates based on the same type of RS data were positive and strong, whereas the correlations between estimates using different sources of RS data were not as strong, and weaker for mean height than for mean diameter and volume. The implications of such correlations in composite estimation are demonstrated and it is discussed how correlations may affect results from data assimilation procedures.

This paper investigates the applicability of deep learning models for predicting the severity of forest wildfires, utilizing an innovative benchmark dataset called EO4WildFires. EO4WildFires integrates multispectral imagery from Sentinel-2, SAR data from Sentinel-1 and meteorological data from NASA Power annotated with EFFIS data for forest fire detection and size estimation. Resulting in a coverage of 45 countries (Figure \ref{Figure1-events}) with a total of 31730 wildfire events from 2018 to 2022. All these various sources of data are archived into data cubes, with the intention of assessing wildfire severity by considering both current and historical forest conditions, utilizing a broad range of data including temperature, precipitation, and soil moisture. The experimental setup has been arranged to test different deep learning architectures’ effectiveness in predicting the size and shape of wildfire burned areas. The study incorporates both Image Segmentation networks and Visual Transformers, employing a consistent experimental design across various models to ensure comparability of results. Adjustments were made to the training data, such as the exclusion of empty labels and very small events, to refine the focus on more significant wildfire events and potentially improve prediction accuracy. The models’ performance was evaluated using metrics like F1 Score, IoU Score, and Average Percentage Difference (aPD). These metrics offer a multi-faceted view of model performance, assessing aspects such as precision, sensitivity, and the accuracy of the burned area estimation. Through extensive testing with Image Segmentation networks and Visual Transformers, the research not only aims at enhancing the accuracy of estimating the burned area but also underscores the significance of quality training data and the comparative effectiveness of traditional segmentation methods over transformer-based models for this specific application. The dataset is published with an Open Access license and is hosted at: \url{10.5281/zenodo.7762564}.

: This study aimed to validate the effects of self-compassion-based forest healing therapy as an intervention for reducing stress and promoting coping resources. Therefore, we investigated the effects of self-compassion-based forest healing therapy on stress, self-compassion, and connectedness to nature. A total of 30 participants were divided into an experimental and control group. Two sessions of forest healing meditation activities were held at the Forest of Healing every two weeks between October and November 2023. As a repeated measures experiment, data were collected before the intervention, after the first intervention, and after the second intervention. Perceived stress, positive and negative affect, and salivary cortisol were measured to assess physiological and psychological stress in participants. Connectedness to nature and self-compassion were measured to evaluate stress-coping resources. The results showed that the forest healing program had significant positive effects on stress and emotional states in the experimental group after the intervention. Further, there was a significant incremental effect on connectedness to nature and self-compassion in the experimental group. Therefore, self-compassion meditation-based forest healing therapy is a feasible and efficient approach for facilitating stress management and coping resource building.

Lettuce is a salt-sensitive crop and has a threshold electrical conductivity of 1.3–2.0 mS cm-1 and above that is considered detrimental. As there has been very little information on the physio-logical response of different critical stages of lettuce under different salt stress (SS), the current study is focused on investigating the effects of SS on the critical physiological traits influencing the carbon assimilation in different growth stages of lettuce. The experiment was conducted in deep-water culture hydroponic system in a greenhouse condition. Four levels of sodium chloride salt treatments (EC: 20, 16, 8, and 1.8 mS cm-1) were applied. During both growth stages (day 11 (GS1) and day 19 (GS2) after salt treatment), the leaf transpiration rate, stomatal conductance, and intercellular CO2 were severely decreased. However, the carbon assimilation rate remained unchanged under SS. Similarly, the water use efficiency increased under the SS. It is concluded that the increasing SS increased stomatal and non-stomatal limiting factors during GS1 suggesting the enhanced limitation in photosynthetic activity while no such trend was observed during GS2. The decreased gm with increased SS at GS1 and GS2 suggested that SS induced the irreversible decrease of gm, which in turn can be responsible for the transient reduction in the Vcmax and Jmax during GS2. Taken together, the evidence from this research recommends that varying the SS levels can significantly affect the physiological performance of lettuce at both growth stages.

Abstract: Background: We previously found that forest bathing significantly reduced the scores for negative emotions and in-creased the score for vigor in the profile of mood states (POMS) test in both males and females and increased the sero-tonin level in males, indicating the potential for beneficial effect on depressive status. In the present study, we investi-gated the effects of forest bathing on the levels of serotonin, oxytocin and insulin-like growth factor I (IGF-1) in blood, Self-Rating Depression Scale (SDS) scores, POMS, subjective fatigue symptoms and subjective sleep quality in female subjects with depression/depressive tendencies. Methods: Thirty-one female subjects aged 40.1±2.4 years with depression/depressive tendencies were recruited after obtaining informed consent. These subjects took day trips to a forest park, the birthplace of forest bathing in Japan named Akasawa Shizen Kyuyourin in Nagano Prefecture, and to a city area of Nagano Prefecture as a control in June 2023. On both trips, they walked 2.2-2.5 km for two hours each in the morning and afternoon on Saturday and Sunday, respectively. Blood was sampled in the afternoon before and after each trip. Concentrations of serotonin, oxytocin, IGF-1 and lactic acid in blood were measured. The SDS scores, POMS test, and questionnaires for subjective fatigue symptoms and subjective sleep quality were conducted before and after the trips. Ambient temperature and humidity were monitoring during the trips. The Nippon Medical School Central Ethics Committee approved this study. Results: Forest bathing significantly decreased SDS scores and the effect lasted for one week after forest bathing. Forest bath-ing also significantly increased the level of serotonin in serum in subjects who were not taking antidepressants, significantly increased the levels of oxytocin and IGF-1 in blood, significantly increased the scores for vigor-activity and friendliness and de-creased the scores for anger-hostility, confusion-bewilderment, fatigue-inertia, tension-anxiety, depression-dejection and total mood disturbance compared with city walking (all p

Soil secondary salinization has seriously affected the greenhouse vegetable production in China. To improve the secondary salinization greenhouse soil and enhance the soil physical-chemical properties in an eco-environmental way, different organic amendments (straw, straw biochar, Trichoderma bio-organic manure, commercial organic manure) were applied using pot experiment for 60 day to comprehensively screen the optimal remediation method. In this study, soil nutrient condition and salt movement were assessed, and predictive models using multi-linear regression (MLR) and Random Forest (RF) were developed to estimate soil salinization parameters. The findings indicated a significant decrease in soil salt content following the application of organic materials compared to the control treatment. Specifically, the addition of straw at a rate of 250g/kg resulted in a 59.38% reduction in soil salt levels after 60 days (P < 0.05). Furthermore, the main salt ions exhibited dynamic changes over the course of the experiment, with reductions observed in Na+, Ca2+, Cl-, and NO3- content under the 250 g/kg straw treatment by 83.63%, 74.67%, 63.26%, 59.07%, respectively, compared to CK (P < 0.05). In addition, the SO42- content under 125 g/kg commercial organic manure amendment reduced by 48.94%, respectively (P < 0.05). Contrary to expectations, the addition of organic materials significantly increased the levels of total nutrients (N/P/K) and available potassium (AK) and phosphorus (AP) in the soil. Specifically, the addition of straw at a rate of 250 g/kg resulted in increases of 18.02%-87.38% in total potassium (TK), 66.67%-200% in total phosphorus (TP), and 142.87%-367.8% in AK after a period of sixty days (P < 0.05). Ultimately, the treatment involving the addition of 250 g/kg of straw demonstrated the most pronounced impact on the physical and chemical properties of the soil. The random forest method shows promise in accurately predicting soil salt and soil sodium adsorption ratio (SAR)indicators, thereby providing a valuable tool for estimating soil properties.

The 2030 global agenda of the United Nations emphasizes peace, human rights, gender equality, partnership, and women's empowerment. It balances the social, economic, and environmental dimensions of sustainable development. The SDG framework was designed to be integrated and indivisible, making the interconnections of 17 Goals and 169 Sustainable Development Goals Targets (SDTs) more complex that need extensive and intensive investigative research. Recent studies have increased on the interrelationships of SDGs, but none of these have focused on integrating Climate Change (CC), Sustainable Forest Management (SFM), and Information and Communication Technology (ICT), also known as CSI Nexus. This study aims to investigate and identify the 169 SDTs linked to CC, SFM, and ICT and assesses the significance of the relationships between these variables. The alignment of SDTs to CSI Nexus was identified through clustering and mapping techniques. The result argued that 56 SDTs are directly connected within CC+SFM+ICT, 16 within CC+SFM, one within SFM+ICT, and 51 within ICT+CC. Our result suggests that CC is significantly associated with SFM; however, ICT has no significant association with CC and SFM. It further asserts that the ICT and SFM have minimal influence on the SDG 2030 framework. The proposed CSI Nexus and SDTs Integration Framework was a science-informed guide for priority-setting, policy coherence, and decision-making supporting the 2030 Sustainable Development Goals. This study does not include interactions, network analysis and visualization, simulations, and modeling between SDG targets.

The bivalve mollusk, Anadara tuberculosa (Black Shell, in Spanish Concha prieta, "CP"), is found on America's Pacific coast, where it is harvested for subsistence and commercial markets. This paper aims to diagnose the performance of the black shell's value chain. We also identify several challenges that must be addressed to improve the sustainability of the black shell fishery in Ecuador. The descriptive methodology was quantitative, with a non-experimental, field, cross-sectional, and ex post facto design. Similar questionnaires were designed, validated, and applied to each link in the production chain to collect information. The performance of the value chain was diagnosed in the dimensions of productivity, competitiveness, and quality of life, reaching a 75.1% index, a result that indicates that the value chain has a moderate to good performance level. However, the value chain can be improved if the following challenges are met: 1) Restoration of the mangrove ecosystem, 2) Promotion of low-intensity shellfish aquaculture, 3) Good sanitary management and purification, 4) Promotion of value-focused ventures, 5) Strengthening of organizations and agreements for the use and custody of mangroves, and 6) Strengthening of institutions that contribute to the advancement of these challenges.

Gesture recognition technology has been quickly developed in the field of human-computer interaction. The multiple-input multiple-output (MIMO) radar has been widely adopted in gesture recognition because of its notable spatial resolution. In this work, a highly accurate MIMO radar-based hand gesture recognition algorithm with very low complexity is proposed. To make the proposed system applicable in the industry and work well even when the size of the training data is limited, we applied several low-complexity adaptive signal processing methods to extract features and reduce the noise effect. First, spectrum analysis is applied to range-Doppler maps (RDMs) and a cell-averaging constant false alarm rate (CA-CFAR) with mirror filters is applied to improve the robustness to noise. Afterward, the features related to the distance, speed, direction, and the elevation angle of the moving object are determined by the proposed adaptive signal analysis techniques and the random forest is applied for classification. The proposed system has the capability to precisely distinguish and identify eight motions, including waving, moving to the left or right, patting, pushing, pulling, and rotating clockwise or anticlockwise, with an accuracy of 95%. Experiments demonstrate the capability of the proposed hand gesture recognition system to classify different movements precisely.

When the formation flying consists of satellites that are independent from each other and forms a virtual synthetic aperture telescope that replaces a single large telescope with all of its optical elements it is required mutual coordination between the satellites with high accuracy in order to achieve good optical observations. In this paper we consider the problem of developing a control system for a tetrahedral satellite formation flying representing a synthetic aperture telescope in the geostationary orbit for high resolution monitoring of fire in the forest area in infrared spectrum. Synthesizing the image with good quality requires to keep the configuration of formation with µm-class accuracy. Study of dynamics of passive uncontrolled motion of formation flying showed a significant deviation of the configuration from the required shape with a high frequency due to the action of gravitational forces. To keep the configuration in the required form with µm accuracy the analysis of efficiency of various controllers was carried out in the process of numerical simulation. The simulation results made it possible to highlight the features of using various approaches to the development of control system for the satellite formation flying representing a synthetic aperture telescope.

Little is known about how differences in water availability within the “super humid” tropics can influence the distribution of understory plant species and the composition of understory plant communities. We investigated variation in the physiological drought tolerances of understory plants and plant communities across a large elevation and precipitation gradient. We established 58 understory plots along a gradient of 400 – 3600 m asl elevation and 1000 – 6000 mm yr-1 rainfall in and around Manu National Park in southeastern Peru. Within the plots, we sampled all understory woody plants and measured three metrics of physiological leaf drought tolerance - turgor loss point (TLP), cuticular conductance (Gmin), and solute leakage (SL) - and assessed how the community-level means of these traits related to mean annual precipitation (MAP) and elevation (in the study gradient temperature decreases linearly and vapor pressure deficit increases monotonically with elevation). We did not find any correlations between the three metrics of leaf drought tolerance, suggesting that they represent independent strategies for coping with low water availability. Despite being widely used metrics of leaf drought tolerance, neither TLP nor Gmin showed any significant relationships with elevation or MAP. In contrast, SL, which has only recently been developed for use in ecological field studies, increased significantly at higher precipitations and at lower elevations (i.e., plants in colder and drier habitats have lower SL, indicating greater drought tolerances). Our results illustrate that differences in water availability may play a strong role in structuring plant communities even in in the wet tropics and highlight the potential for SL assays to be an efficient and effective tool for measuring drought tolerances in the field.

Remote sensing is one of the modern methods that have significantly developed over the last two decades and nowadays provides a new means for forest monitoring. High spatial and temporal resolutions are demanded for accurate and timely monitoring of forests. In this study multi-spectral Unmanned Aerial Vehicle (UAV) images were used to estimate canopy parameters (definition of crown extent, top and height as well as photosynthetic pigment contents). The UAV images in Green, Red, Red-Edge and NIR bands were acquired by Parrot Sequoia camera over selected sites in two small catchments (Czech Republic) covered dominantly by Norway spruce monocultures. Individual tree extents, together with tree tops and heights, were derived from the Canopy Height Model (CHM). In addition, the following were tested i) to what extent can the linear relationship be established between selected vegetation indexes (NDVI and NDVIred edge) derived for individual trees and the corresponding ground truth (e.g., biochemically assessed needle photosynthetic pigment contents), and ii) whether needle age selection as a ground truth and crown light conditions affect the validity of linear models. The results of the conducted statistical analysis show that the two vegetation indexes (NDVI and NDVIred edge) tested here have a potential to assess photosynthetic pigments in Norway spruce forests at a semi-quantitative level, however the needle-age selection as a ground truth was revealed to be a very important factor. The only usable results were obtained for linear models when using the 2nd year needle pigment contents as a ground truth. On the other hand, the illumination conditions of the crown proved to have very little effect on the model’s validity. No study was found to directly compare these results conducted on coniferous forest stands. This shows that there is a further need for studies dealing with a quantitative estimation of the biochemical variables of nature coniferous forests when employing spectral data acquired by the UAV platform at a very high spatial resolution.

In-depth insights into the profound impacts of climate change and human activities on water resources are garnered through the dynamic changes in surface water, a crucial aspect of effective water resource management and the preservation of aquatic ecosystems. This paper introduces an innovative approach employing the random forest algorithm for the systematic extraction and monitoring of surface water at large regional or national scales. This method integrates spectral bands, spectral indices, and digital elevation model data, offering a novel perspective on this critical task. A data filling model is proposed to mitigate the impact of missing data due to cloud cover. Leveraging the capabilities of the Google Earth Engine (GEE), detailed information on surface water dynamics during the rainy and dry seasons in the Yangtze River Basin (YRB) from 1991 to 2021 is extracted using Landsat time series imagery. The analysis encompasses spatial-temporal variation characteristics and trends, with a specific focus on the intricate interplay between the areal extent of surface water and hydro-meteorological factors in each sub-basin of the YRB. Importantly, this includes considerations of potential groundwater contributions to surface water. Key findings from our research include: (1) Achieving a remarkable overall accuracy of 0.96 ± 0.03 in obtaining reliable surface water datasets with the support of GEE. (2) Identifying significant trends, such as a noteworthy increase in rainy season surface water bodies (+248.0 km2·yr−1) and a concerning decrease in surface ice/snow cover during both rainy and dry seasons, with change rates of −39.7 km2·yr−1 and −651.3 km2·yr−1, respectively. (3) Uncovering the driving mechanisms behind these changes, revealing positive correlations between the areal extent of rainy season surface water bodies and precipitation, as well as negative correlations between surface ice/snow cover area and average surface skin temperature. It is crucial to note that these driving factors exhibit variation among secondary river systems, underscoring the complexity of surface water dynamics. Furthermore, comparative analyses with existing surface water products are conducted, contributing to a deeper understanding of the advantages and uncertainties inherent in our proposed extraction method. The proposed method for large-scale surface water extraction not only enhances the monitoring of spatio-temporal surface water dynamics in the YRB but also provides valuable insights for the sustainable utilization and protection of water resources, considering the potential role of groundwater in supplementing surface water.

The author attempts to reconstruct the climatic vicissitudes of the Mediterranean to explain why only broadly distributed Eurasian forest species have penetrated the Mediterranean peninsulas. He has carried out a bibliographic survey of the status of breeding forest birds in Italy over 15 decades (1872-2022) in order to establish an objective long-term trend (stable, increasing, decreasing, etc.). The number of breeding forest birds in Italy amounts to 61; their distribution, with a few exceptions, indicates that they are widespread in Eurasia, but only a small percentage of Eurasian forest species have colonized Italy and the other Mediterranean peninsulas, namely 49 in Iberian, 61 in Italian and 64 in Balkan peninsulas; a small percentage of them (between 10.9 and 14.3%) belongs to trans-Saharan migrants. The similarity between the forest species on the three peninsulas (Iberian, Italian and Balkan) results between 0.45 and 0.48, indicating a certain differ-ence in the overall fauna on the three territories. Not all species have penetrated southwards into the three peninsulas; for example, some that stopped in the Italian Alps have instead arrived to the forests of Greece, at a latitude corresponding to southern Italy, or species that in Italy stopped in the northern Apennines in the other two peninsulas have instead arrived far south. Iberian peninsula and the island of Corsica hold three endemic species among breeding forest birds, Italian and Balkan peninsulas have not endemic species. Overall, the Mediterranean presently hosts mainly neo-endemic taxa among forest bird species; the only paleo-endemics can be considered the three species of nuthatches living in Corsica, Algeria, and Turkey (other than Caucasus and the islet of Lesvos) and Le Vaillant’s woodpecker in the Maghreb (North Africa). Italian forests cover ca. 40% of land surface and since 1980’ are increasing, but 22% of them do not have a natural origin. However, it is difficult to know the true increase of forests, because some of them are fired every year. The presence of some ecologically demanding forest birds depends on the age of the trees, permanent open spaces and other characteristics at the edge of woodland.

Mining for resources extraction may lead to several geological and associated environmental changes due to ground movements, collision with mining cavities and deformation of aquifers. Geological changes may continue in a reclaimed mine area, and the deformed aquifers may entail a breakdown of substrates and an increase in ground water tables, which may cause surface area inundation. Consequently, a reclaimed mine area may experience surface area collapse, i.e. subsidence, and degradation of vegetation health. Thus, monitoring short-term landscape dynamics in a reclaimed mine area may provide important information on the long-term geological and environmental impacts of mining activities. We studied landscape dynamics in Kirchheller Heide, Germany, which experienced extensive soil movement due to longwall mining without stowing, using Landsat imageries between 2013 and 2016. A Random Forest image classification technique was applied to analyse land-use and land-cover dynamics and the growth of wetland areas was assessed using a Spectral Mixture Analysis (SMA). We also analyzed the changes in vegetation health using a Normalized Difference Vegetation Index (NDVI). We observed a 19.9% growth of wetland area within the four years with 87.2% of growth in the coverage of two major waterbodies in the reclaimed mine area. NDVI values indicate that 66.5% of the vegetation of the study area was degraded due to changes in ground water tables and surface flooding. Our results inform environmental management and mining reclamation authorities about the subsidence spots and priority mitigation areas from land surface and vegetation degradation in Kirchheller Heide.

The aim of this study is to evaluate three different strategies to improve classification accuracy in a highly fragmented semiarid area. i) Using different classification algorithms: Maximum Likelihood, Random Forest, Support Vector Machines and Sequential Maximum a Posteriori, with parameter optimisation in the second and third cases; ii) using different feature sets: spectral features, spectral and textural features, and spectral, textural and terrain features; and iii) using different image-sets: winter, spring, summer, autumn, winter+summer, winter+ spring+summer; and a four seasons combination. A 3-way ANOVA is used to discern which of these approaches and their interactions significantly increases accuracy. Tukey-Kramer contrast using a heteroscedasticity-consistent estimation of the kappa covariances matrix was used to check for significant differences in accuracy. The experiment was carried out with Landsat TM, ETM, and OLI images corresponding to the period 2000-2015. A combination of four images was the best way to improve accuracy. Maximum Likelihood, Random Forest and Support Vector Machines do not significantly increase accuracy when textural information is added, but do so when terrain features are taken into account. On the other hand, Sequential Maximum a Posteriori increases accuracy when textural features are used, but reduces accuracy substantially when terrain features are included. Random Forest using the three feature subsets and Sequential Maximum a Posteriori with spectral and textural features had the largest kappa values, around 0.9.

Cumulative effects of landscape disturbance in forested source water regions can alter the storage of fine sediment and associated phosphorus in riverbeds, shift nutrient dynamics and degrade water quality. Here, we examine longitudinal changes in major element chemistry and particulate phosphorus (PP) fractions of river-bed sediment in an oligotrophic river during environmentally sensitive low flow conditions. Study sites along 50 km of the Crowsnest River were located below tributary inflows from sub-watersheds and represent a gradient of increasing cumulative sedi-ment pressures across a range of land disturbance types (harvesting, wildfire, and municipal wastewater discharges). Major elements (Si2O, Al2O3, Fe2O3, MnO, CaO, MgO, Na2O, K2O, Ti2O, V2O5, P2O5), loss on ignition (LOI), PP fractions (NH4CI-RP, BD-RP, NaOH-RP, HCI-RP and NaOH(85)-RP) and absolute particle size were evaluated for sediments collected in 2016 and 2017. While total PP concentrations were similar across all sites, bioavailable PP fractions (BD-RP, NaOH-RP) increased downstream with increased concentrations of Al2O3 and MnO and levels of landscape disturbance. This study highlights the longitudinal water quality impacts of increasing landscape disturbance on bioavailable PP in fine riverbed sediments and shows how the convergence of climate (wildfire) and anthropogenic (sewage effluent, harvesting, agriculture) drivers can produce legacy effects on nutrients.

Understory plants are important components of forest ecosystem productivity and diversity. Compared to biomass models of overstory canopy trees, few are available for understory saplings and shrubs and therefore their roles in estimation of forest carbon pools are often ignored. In this study, we harvested 24 understory species including 4 saplings, 9 tree-like shrubs and 11 typical shrubs in coniferous and broadleaved mixed forest in northeastern China and developed the best fit allometric equations of above- and below-ground and total biomass by species-specific or multispecies using morphological measurements of basal diameter, height and crown area as independent variables. The result showed that single basal diameter, height or crown area had good explanatory power for both species-specific and multispecies (p<0.001). The best-fit models included only basal diameter in sapling and tree-like shrubs, and combinations of crown area, height, and basal diameter in typical shrubs. The logarithmic model was most desired among the 4 model forms of linear, quadratic, multiple linear and logarithmic, for species-specific and multispecies. The models we developed should help the estimation of forest ecosystem carbon stocks, especially for belowground component, and provide tools for quantification of individual species biomass of understory plants.

Our study is part of the ongoing discussion concerning influencer marketing as there seems to have been a shift and social media marketing is bigger than ever. Social media outlets are excellent vehicles for fostering relationships with consumers who can be susceptible to influencer advertising. Therefore, companies now pay for posts on users’ profiles to generate popularity for products. How this approach affects consumers’ buying behavior is an interesting research question. We reference Herbert Simon’s economics of attention as an appropriate theoretical construct for describing the reality of the internet. Based on unique survey data from 513 Polish respondents, the study applies econometric methods and supervised and unsupervised machine learning techniques to identify the primary consumer groups with different characteristics of engagement and sensitivity to influencer activities, revealing the possible drivers of purchase intent. The findings provide valuable insights into consumers’ informational preferences, demonstrating how social media influencers may attract attention and drive sales.

An information-theoretic data mining method is employed to analyze categorical spatiotemporal Geographic Information System land use data. Reconstructability Analysis (RA) is a maximum-entropy-based data modeling methodology that works exclusively with discrete data such as those in the National Land Cover Database (NLCD). The NLCD are organized into a spatial (raster) grid, and are available in consistent format for every five years from 2001 to 2021. An NLCD tool reports how much change occurred for each category of land use; for the study area examined the most dynamic class is Evergreen Forest (EFO), so the presence or absence of EFO in 2021 was chosen as the dependent variable that our data modeling attempts to predict. RA predicts the outcome with approximately 80% accuracy using a sparse set of cells from a spacetime data cube consisting of neighboring lagged-time cells. When the predicting cells are all Shrubs &amp; Grasses there is a high probability for a 2021 state of EFO, while when the predicting cells are all EFO, there is a high probability that the 2021 state will be not-EFO. These findings are interpreted as detecting forest clear-cut cycles that show up in the data, and explain why this class is so dynamic. This study introduces a new approach to analyzing GIS categorical data and expands the range of applications that this entropy-based methodology can successfully model.

Every year, the Montreal police are confronted with countless crimes committed by criminals. These crimes affect the quality of life of city residents and impose a socio-economic burden on the city. In this study, we conduct a comparative analysis based on several machine learning algorithms to develop a model to predict the crime category in Montreal. The performance of algorithms such as eXtreme Gradient Boosting (XGBoost), Decision Trees (DT) and Random Forest (RF) were analyzed. The performance analysis takes into account the performance metrics such as precision, accuracy, recall and F1-score. This analysis was based on crime data in Montreal from 2015 to 2023. This data is characterized by a strong imbalance between crime categories. To address the data imbalance problem, a data balancing approach based on the SMOTE-ENN algorithm was adopted. In the exploratory data analysis phase, temporal trends by crime category were highlighted. The results of the analysis showed that the XGBoost algorithm outperformed the other two. Specifically, the XGBoost algorithm achieves an accuracy of 92%, while DT and RF achieve an accuracy of 86% and 84%, respectively. As a result, XGBoost was deployed via a web application using the Flask and Swagger UI Python frameworks. This study provides the Montreal police with an effective tool to better utilize their resources in fighting crime. In addition, policymakers in the city of Montreal can use this tool to identify high-risk areas and give them more attention.

The arguments on the origin and evolution of the evergreen broad-leaved forest in eastern Asia, especially in the evolutionary process, exist generally, even contrary in some cases. The origin and evolution of the flora of eastern Asia, the formation time of Asian monsoon, and the implications from phylogenetic and molecular biogeographic studies in some important taxa, as well as in palaeobotanical evidences, are debatable. Most researches from different disciplines suggested that the monsoon in Miocene is a key to diversification of eastern Asian flora and its evergreen broad-leaved forest. The common view is that the evergreen broad-leaved forest of East Asia is closely related to the monsoon intensity and developments, which are caused by the uplift of Himalaya-Tibet, during or after the mid-Miocene. The analysis on the floristic elements show that the present subtropical evergreen broad-leaved forest in eastern Asia could have an early or ancient tropical origin and a tropical Asian affinity, but their species are dominated by the Chinese endemic or eastern Asian distribution, many of which are the tropical sister ones. The time of Himalayan uplift and intensity of monsoon climate is believed the key for the formation of the evergreen broad-leaved forest in eastern Asia. Combined existing palaeobotanical findings, the uplift of Himalayas and the formation of monsoon climate, as well as floristic elements of the subtropical evergreen broad-leaved forest, we believe that it was evolved from a Asian tropical rain forest after mid-Miocene in southeastern region of eastern Asia, while the ancient subtropical evergreen broad-leaved forests in southwestern region continuously evolved into the present subtropical ones.

The 21st century has seen the launch of new space-borne sensors based on LiDAR (light detection and ranging) technology developed in the second half of the 20th century. LiDAR was initially developed to integrate laser-focused imaging with the capability to determine distances through the measurement of signal return times, utilizing suitable sensors and data acquisition electronics. Nowadays, these sensors have transformed into robust instruments, offering novel opportunities for mapping terrain, canopy heights, and estimating above-ground biomass (AGB) across local to regional scales. This work aims to analyze the scientific impact of these sensors on large-scale for-est mapping to retrieve 3D canopy information, monitor forest degradation, estimate AGB, and model key ecosystem variables such as primary productivity and biodiversity. In this way, a worldwide bibliometric analysis of this topic was carried out based on up to 412 publications in-dexed in the Scopus database during the period 2004-2022. The results showed that the number of published documents increased exponentially in the last five years, coinciding with the commis-sioning of two new LiDAR space missions: Ice, Cloud and Land Elevation Satellite (ICESat-2) and Global Ecosystem Dynamics Investigation (GEDI). These missions are providing data since 2018 and 2019, respectively. The journal that demonstrated the highest productivity in this field was "Remote Sensing," and among the leading contributors, the top five countries in terms of publica-tions were the USA, China, the UK, France, and Germany. In the realm of prominent research in-stitutions, France boasted six, the USA had four, China had three, while the UK and Canada each had one. The upward trajectory in the number of publications recorded from 2004 to 2022 catego-rizes the subject under investigation as a highly trending research topic, particularly within the context of enhancing the administration of forest resources and engaging in global climate treaty frameworks mandating the surveillance and reporting of carbon stocks in forests. The recent launch in August 2022 of the Terrestrial Ecosystem Carbon Monitoring Satellite (TECMS; China State Administration of Forestry and Grassland), along with the planned launch in the coming years of up to three new space sensors, such as the Multi-footprint Observation LiDAR and Im-ager (Japan Aerospace Exploration Agency), the BIOMASS P-band Synthetic Aperture Radar (SAR) (European Space Agency), and the LiDAR Surface Topography (LIST; NASA), will greatly contribute to expanding the ability to map and monitor forest systems at very large scales. In this context, the integration of space-borne data, including imagery, SAR, and LiDAR, is anticipated to steer the trajectory of this research in the upcoming years.

In order to enhance the comfort of cycling, it is imperative to investigate the effects of vibration on non-motorized bicycle riding from the perspectives of road characteristics and traffic features. Through an analysis of the mechanisms by which road and traffic conditions influence cycling vibrations, 13 influencing factors were identified. Subsequently, the non-motorized bicycle lanes in Wuhan city were selected as the subject of empirical research, where three-axis accelerometers attached to the rider's torso were employed to measure and categorize vibration comfort levels. The experimental road segments were found to exhibit comfort levels falling between slightly uncomfortable and relatively uncomfortable. Further analysis of the influencing factors was conducted using the Random Forest algorithm and Logistic Regression. The results revealed that six factors significantly impact the comfort of cycling: the presence of dedicated non-motorized bicycle lanes, the absence of physical separation between non-motorized and motorized traffic, cycling speed, the number of road surface irregularities, the presence of parking areas within the non-motorized bicycle lane, and the type of non-motorized bicycle. This study provides valuable insights into the factors affecting non-motorized bicycle lane usage and contributes to the refined design of urban non-motorized bicycle infrastructure, thereby facilitating better support for sustainable urban transportation.

Tesso Nilo National Park is one of the protected areas designated as KPA by the Decree of the Minister of Forestry No.225/Menhut-II/2004 dated July 19, 2004 covering an area of ​​38,576 ha, then expanded again through the Decree of the Minister of Forestry No.663/Menhut/2009 dated 19 October 2009 with an area of ​​± 83,068 ha. The Tesso Nilo National Park area is experiencing the dynamics of land cover changes, namely the conversion of forest land which causes the forest area to become increasingly narrow in this area. With the reduction in forest area in this area, it causes a decrease in ecosystem network connectivity due to forest fragmentation that occurs, so that forests are separated and further apart. This study aims to analyze changes in land cover in the Tesso Nilo National Park area to find out information on changes in habitat ecosystems in the last 20 years. the observations were made using satellite images in 1999, 2010 and 2019. so that it can be seen the effect of forest fragmentation on ecosystems in the Tesso Nilo National Park area. From the results of the analysis, it was found that the area of ​​forest cover in the Tesso Nilo National Park decreased from 1999 to 2019 and caused changes in the connectivity network of forest ecosystems, which was found in the study, the weakest connectivity separated forest fragments as far as 17394.47 meters due to forest cover fragmentation.

Breast cancer is the most common malignancy in women worldwide. The pathogenesis of this disease is closely related to the estrogen receptor alpha subtype (ERα). Therefore, it is of great importance to develop effective inhibitors of ERα activity for the treatment of breast cancer. In this paper, we propose a novel ensemble machine learning model for quantitative structure-activity relationship of anti-breast cancer drugs, which can effectively predict drug activity in small samples with multiple characteristic variables. To avoid the problem of over-fitting caused by low-correlation independent variables, the scoring mechanism of random forest was improved by incorporating three relevance indicators, including the maximum mutual information number, Pearson correlation coefficient and distance correlation coefficient, and 20 optimal molecular descriptors were selected. The Bayesian hyperparameter optimization method was used to optimize the parameters of multiple linear regression (MLR), support vector regression (SVR), and extreme gradient boosting (XGBoost), respectively. The AdaBoost strong learner was constructed by combining the weak learner with the weighted linear addition method. The results show that the proposed ensemble learning model has the best prediction performance compared to the three basic learner models and the CNN-LSTM combination prediction model. The root mean square error was reduced by 7.60%-26.51%. The mean relative error was reduced by 6.46%-30.92%. Goodness of fit increased by 9.57%-36.94%. Finally, the biological activities of 50 candidate compounds for ERα inhibitors were predicted, and it was found that 4-[2-benzyl-1-[4-(2-pyrrolidin-1-ylethoxy)phenyl]but-1-enyl]phenol had an excellent biological activity value pIC50, which had the potential to be an ERα inhibitor. The model proposed in this paper has good prediction accuracy, which can provide an effective reference for the discovery and development of anti-breast cancer drugs.

This paper expressed three regression models that predict the lithium-ion battery life for electric cars based on a supervised machine-learning regression algorithm. The Linear Regression, Bagging Regressor, and Random Forest Regressor models will be compared for capacity prediction of lithium-ion batteries based on voltage-dependent per-cell modeling. When sufficient test data is available, three linear regression learning algorithms will train this model to give a promising battery capacity prediction result. The effectiveness of the three linear regression models will be demonstrated experimentally. The experiment table system is built with an NVIDIA Jetson Nano 4GB Developer Kit B01, a battery, an Arduino, and a voltage sensor. The Random Forest Regressor model has evaluated the model's accuracy based on the average of the square of the difference between the initial value and the predicted value in the data set (MSE (Mean Square Error)), and RMSE (Root Mean Squared Error) is smaller than the Linear Regression model, Bagging Regressor model (MSE is 516.332762; RMSE is= 22.722957). The Linear Regression model with MSE and RMSE is the biggest (MSE is 22060.500669; RMSE is= 148.527777). This result allows the Random Forest Regressor model to remain a helpful life prediction of lithium-ion batteries. Moreover, this result allows rapid identification of battery manufacturing processes and will enable users to decide to replace defective batteries when deterioration in battery performance and lifespan are identified.

This study addresses the limited coverage of regulatory monitoring for particulate matter 2.5 microns or less in diameter (PM2.5) in Thailand due to the lack of ground station data by developing a model to estimate daily PM2.5 concentrations in small regions of Thailand using satellite data at a 1-kilometer resolution. The study employs multiple linear regression and three machine learning models and finds that the random forest model performs the best for PM2.5 estimation over the period of 2011-2020. The model incorporates several factors such as Aerosol Optical Depth (AOD), Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Elevation (EV), Week of the year (WOY), and year and applies them to the entire region of Thailand without relying on monitoring station data. Model performance is evaluated using the coefficient of determination (R2) and root mean square error (RMSE), and the results indicate high accuracy for training (R2: 0.95, RMSE: 5.58 μg/m3), validation (R2: 0.78, RMSE: 11.18 μg/m3), and testing (R2: 0.71, RMSE: 8.79 μg/m3) data. These PM2.5 data can be used to analyze the short- and long-term effects of PM2.5 on population health and inform government policy decisions and effective mitigation strategies.

Through this study, we established equations for estimating the standing tree carbon stock, based on 24 tree species in multiple size classes in a case study at the Ngao Demonstration Forest (NDF) in northern Thailand. Four hundred thirty-nine wood samples from trees in mixed deciduous forest (MDF), dry dipterocarp forest (DDF), and dry evergreen forest (DEF), were collected using non-destructive methods to estimate above-ground carbon equations through statistical regression. The equations were established based on four criteria: 1) the coefficient of determination (R2), 2) Standard error of estimate (SE), 3) F-value, and 4) Significant value (p-value, α ≤ 0.05). The above-ground carbon stock (C) equations for standing trees in the MDF was C = 0.0199DBH2.1887H0.5825, for DDF was C = 0.0145DBH2.1435 H0.748, for DEF was C = 0.0167DBH2.1423H0.7070, and the general equation for all species/wood density groups was C = 0.017543DBH2.1625H0.6614, where DBH is tree diameter at breast height and H is tree total height. The above-ground carbon stock in the DDF, MDF, and DEF was 142, 53.02, and, 12 tons/ha, respectively, and the estimated above-ground carbon stock in the Mae Huad sector at the NDF was 61 tons/ha.

In recent years, the ecological and economic values of forest plants have been gradually recognized worldwide. However, the growing global demand for new forest plant varieties with higher wood production capacity and better stress tolerance cannot be satisfied by conventional phenotype-based breeding, marker-assisted selection, and genomic selection. In the recent past, diverse omics technologies, including genomics, transcriptomics, epigenomics, proteomics, and metabolomics, have been developed rapidly, providing powerful tools for the precision genetic breeding of forest plants. Genomics lays a solid foundation for understanding complex biological regulatory networks, while other omics technologies provide different perspectives at different levels. Multi-omics integration has combined the different omics technologies, becoming a powerful tool for genome-wide functional element identification in forest plant breeding. This review summarizes the recent progress of omics technologies and their applications in the genetic studies of forest plants. It will provide forest plant breeders with an elementary knowledge of multi-omics techniques for future breeding programs.

Immersive experiences in green areas and particularly in forests have long been known to produce beneficial effects for human health. However, the exact determinants and mechanisms leading to healthy outcomes remain to be elucidated. The purpose of this study was to investigate whether inhaling plant-emitted biogenic volatile compounds, namely monoterpenes (MTs), can produce specific effects on anxiety. Data from 505 subjects participating in 39 structured forest therapy sessions in different Italian sites, were collected. Monoterpenes air concentration was measured at each site. STAI State questionnaires were administered before and after the sessions as a measure of anxiety. A propensity score matching analysis was then performed, considering an above-average exposure to inhalable air MTs as the treatment: the estimated effect was -1.28 STAI-S points (95% C.I. -2.51 to -0.06, p = 0.04), indicating that the average effect of exposure to high MT air concentrations during forest therapy sessions is to decrease anxiety.

The seasonal and vertical spatial variation characteristics of total N, NH4+—N and NO3-—N in the soil in Picea mongolica forest at different stand ages were studied. The results showed that: (1) NH4+ —N in the soil in Picea mongolica forest was positively correlated with sample date, soil NO3-—N and forest age (P <0.05), and negatively correlated with soil depth (P < 0.01). NO3-—N in the soil in Picea mongolica forest was negatively correlated with sample date and forest age (P < 0.05), and significantly negatively correlated with soil depth (P < 0.01); (2) the content of NH4+—N is greater than that of NO3-—N in each soil layer of Picea mongolica forest at three forest ages. The correlation analysis showed which had an impact on the content of NH4+—N and NO3-—N in the soil in Picea mongolica forest. The content was lower in February and November, and higher in May and August；(3) The contents of total N, NH4+—N and NO3-—N in the soil of Picea mongolica forest in the three forest ages increased with the depth of soil layer (0-50cm), and showed an overall downward trend. The contents of NH4+—N in the soil layer of young forest (0-10cm, 10-20cm and 20-30cm, 30-40cm and 40-50cm) were significantly different (P＜0.05), and the contents of NO3-—N were also significantly different (P＜0.05), while their contents of middle-aged forest and near mature forest increased with the depth of soil layer, There was no significant difference in the content of NH4+—N; (4) The content of NH4+—N in the soil in Picea mongolica forest generally showed the following change trend near mature forest > middle-aged forest > young forest. The change trend of soil NO3-—N content is consistent with that of the content of NH4+—N in the soil in Picea mongolica forest.

Management approaches inspired by the variability of natural disturbances are expected to produce forests in the future that will be significantly more resilient and better adapted to local environmental conditions. Due to climate change, windstorms are becoming increasingly common resulting in the destruction not only of extensive forest areas but, quite often, of small-sized and scattered forest lands that can ultimately become home to insects and disease dissemination sites. In the present study, an attempt is made to identify and record areas in the northeastern forests of Greece covered by mixed stands of conifers and broadleaves that experienced massive windthrow following local storms. Based on tree-level data, local topographic features, forest characteristics and the mechanical properties of green wood, a reliable model, to be used for the prediction of similar disturbances in the future, has been created after a thorough comparative study of the most well-known intelligent machine learning algorithms.

The global carbon neutrality challenge places a spotlight on forests as carbon sinks. However, greenhouse gas (GHG) balances of wood for material and energy use often reveal GHG emission savings in comparison with a non-wood reference. Is it thus better to increase wood production and use, or to conserve and expand the carbon stock in forests? GHG balances of wood products mostly ignore the dynamics of carbon storage in forests, which can be expressed as the carbon storage balance in forests (CSBF). For Germany, a CSBF of 0.25 to 1.15 t CO2/m³ wood can be assumed. When the CSBF is integrated into the GHG balance, GHG mitigation substantially deteriorates and wood products may even turn into a GHG source, e.g. in the case of energy wood. Here, building up the forest carbon sink would be the better option. We conclude that it is vital to include the CSBF in GHG balances of wood products if the wood is extracted from forests. Only then can GHG balances provide political decision-makers and stakeholders in the wood sector with a complete picture of GHG emissions.

During the COVID-19 lockdown in Wuhan, transportation, industrial production and other human activities declined significantly, as did the NO2 concentration. In order to assess the relative contributions of different factors to reductions of air pollutants, sensitivity experiments were implemented by random forest (RF) model, with the comparison of contributions of meteorology, road traffic, and emission sources between different periods. Besides, an emulator was operated to suggest an appropriate limit for control of transportation. The RF models showed different mechanisms for air pollutants. Within-city Migration index (WMI) was more important in the normal, pre-lockdown and post-pandemic model while Out-Migration Index (OMI) was emphasized in the lockdown model. In the COVID-19 lockdown period, 73.3% of the reduction can be attributed to the decreased road traffic, showing massive impact of road traffic on the air quality. In the post-pandemic period, meteorology controlled about 42.2% of the decrease and emissions from industry and household controlled 40.0% while road traffic only contributed to 17.8%. It was suggested that priority of restriction should be given to road traffic within the city. A limit of less than 40% on the control of the road traffic can get a better effect, especially for cities with severe traffic pollution.

The goal of this study was to analyze the forest degradation in the Reserve for San Rafael National Park, Paraguay, during the period 2005-2019. This Reserve is one of the most important forest remnants of the Upper Paraná Atlantic Forest Ecoregion. A multitemporal analysis of degradation was carried out due to the occurrence of three disturbances: forest fires, a twister and illicit crops, using the Continuous Degradation Detection (CODED) algorithm, for which 3 factors were considered: variations due to pixel in the NDFI index values before, during and after every disturbance registered. In this context, the phenomenon with the greatest impact in terms of magnitude of degradation were the forest fires of 2005, being that year at the same time, the one that reported the highest degradation values. Secondly, there are the illicit crops established until the first semester of 2019, and lastly, the twister that occurred in 2017. Our findings demonstrate that CODED algorithm can detect multi-temporal degradation events in a Subtropical Broadleaf Forest, and the post-disturbance regeneration process after every disturbance tends to occur immediately. The response in terms of degradation-regeneration is highly variable, depending of the nature and severity of each disturbance and the vegetation recovery dynamics.

Wrist-worn fitness trackers and smartwatches are proliferating with an incessant attention towards health tracking. Given the growing popularity of wrist-worn devices across all age groups, a rigorous evaluation for recognizing hallmark measures of physical activities and estimating energy expenditure is needed to compare their accuracy across the lifespan. The goal of the study was to build machine learning models to recognize physical activity type (sedentary, locomotion, and lifestyle) and intensity (low, light, and moderate), identify individual physical activities, and estimate energy expenditure. The primary aim of this study was to build and compare models for different age groups: young [20-50 years], middle (50-70 years], and old (70-89 years]. Participants (n = 253, 62% women, aged 20-89 years old) performed a battery of 33 daily activities in a standardized laboratory setting while wearing a portable metabolic unit to measure energy expenditure that was used to gauge metabolic intensity. Tri-axial accelerometer collected data at 80-100 Hz from the right wrist that was processed for 49 features. Results from random forests algorithm were quite accurate in recognizing physical activity type, the F1-Score range across age groups was: sedentary [0.955 – 0.973], locomotion [0.942 – 0.964], and lifestyle [0.913 – 0.949]. Recognizing physical activity intensity resulted in lower performance, the F1-Score range across age groups was: sedentary [0.919 – 0.947], light [0.813 – 0.828], and moderate [0.846 – 0.875]. The root mean square error range was [0.835 – 1.009] for the estimation of energy expenditure. The F1-Score range for recognizing individual physical activities was [0.263 – 0.784]. Performances were relatively similar and the accelerometer data features were ranked similarly between age groups. In conclusion, data features derived from wrist worn accelerometers lead to high-moderate accuracy estimating physical activity type, intensity and energy expenditure and are robust to potential age-differences.

Terrestrial laser scanning (TLS) provides detailed three-dimensional representation of the surrounding forest structure. However, due to close-range hemispherical scanning geometry, the ability of TLS technique to comprehensively characterize all trees and especially the upper parts of forest canopy is often limited. In this study, we investigated how much forest characterization capacity can be improved in managed Scots pine (Pinus sylvestris L.) stands if TLS point cloud is complemented with a photogrammetric point cloud acquired from above the canopy using unmanned aerial vehicle (UAV). In this multisensorial (TLS+UAV) close-range sensing approach, the used UAV point cloud data was considered feasible especially in characterizing the vertical forest structure and improvements were obtained in estimation accuracy of tree height as well as plot-level basal-area weighted mean height (H_g) and mean stem volume (V_mean). Most notably the root mean square error (RMSE) in H_g improved from 0.88 m to 0.58 m and the bias improved from -0.75 m to -0.45 m with the multisensorial close-range sensing approach. However, in managed Scots pine stands the mere TLS captured also the upper parts of the forest canopy rather well. Both approaches were capable of deriving stem number, basal area, V_mean, H_g and basal area-weighted mean diameter with a relative RMSE less than 5.5% for all of the sample plots. Although the multisensorial close-range sensing approach mainly enhanced characterization of forest vertical structure in single-species, single-layer forest conditions, representation of more complex forest structures may benefit more from point clouds collected with sensors of different measurement geometries.

Trace metals can enter some natural regions with low human disturbance from atmospheric circulation, but little information is available regarding how the canopy can retained trace metals. Therefore, a representative sub-alpine spruce plantation was selected to investigate the net throughfall fluxes of eight trace metals (Fe, Mn, Cu, Zn, Al, Pb, Cd and Cr) of closed canopy and gap-edge canopy from August 2015 to July 2016. Over a one-year observational period, the annual fluxes of Al, Zn, Fe, Mn, Cu, Cd, Cr and Pb were 7.29 kg·ha^-1, 2.30 kg·ha^-1, 7.02 kg·ha^-1, 0.16 kg·ha^-1, 0.19 kg·ha^-1, 0.06 kg·ha^-1, 0.56 kg·ha^-1 and 0.24 kg·ha^-1, respectively, in the deposited precipitation. The annual net throughfall fluxes of these trace metals were 1.73 kg·ha^-1, 0.9 kg·ha^-1, 1.68kg·ha^-1, -0.032 kg·ha^-1, 0.04 kg·ha^-1, 0.018 kg·ha^-1, 0.093 kg·ha^-1 and 0.087kg·ha^-1, respectively, in the gap-edge canopy and -1.6 kg·ha^-1, 1.13 kg·ha^-1, 1.65 kg·ha^-1, -0.10 kg·ha^-1, 0.05 kg·ha^-1, 0.03 kg·ha^-1, 0.26 kg·ha^-1 and 0.15 kg·ha^-1, respectively, in the closed canopy. The closed canopy displayed a greater filter effect on the trace metals from precipitation than did the gap-edge canopy in the sub-alpine forest. In the rainy season, the net filtering ratio of trace metals ranged from -66%-89% in the closed canopy and from -52% to 25% in the gap-edge canopy. However, the net filtering ratio of all trace metals was greater than 50% in the closed canopy in the snowy season. Therefore, the results suggested that the most trace metals moving through the forest canopy are taken up rather than by rainfall leaching; moreover, the closed canopy can efficiently take up trace metals in the snowy season.

If given the correct remotely sensed information, machine learning can accurately describe soil moisture conditions in a heterogeneous region at the large scale based on soil moisture readings at the small scale through rule transference across scale. This paper reviews an approach to increase soil moisture resolution over a sample region over Australia using the Soil Moisture Active Passive (SMAP) sensor and Landsat 8 only and a validation experiment using Sentinal-2 and the Advanced Microwave Scanning Radiometer (AMSR-E) over Nevada. This approach uses an inductive localized approach, replacing the need to obtain a deterministic model in favor of a learning model. This model is adaptable to heterogeneous conditions within a single scene unlike traditional polynomial fitting models and has fixed variables unlike most learning models. For the purposes of this analysis, the SMAP 36 km soil moisture product is considered fully valid and accurate. Landsat bands coinciding in collection date with a SMAP capture are down sampled to match the resolution of the SMAP product. A series of indices describing the Soil-Vegetation-Atmosphere Triangle (SVAT) relationship are then produced, including two novel variables, using the down sampled Landsat bands. These indices are then related to the local coincident SMAP values to identify a series of rules or trees to identify the local rules defining the relationship between soil moisture and the indices. The defined rules are then applied to the Landsat image in the native Landsat resolution to determine local soil moisture. Ground truth comparison is done via a series of grids using point soil moisture samples and air-borne L-band Multibeam Radiometer (PLMR) observations done under the SMAPEx-5 campaign. This paper uses a random forest due to its highly accurate learning against local ground truth data yet easily understandable rules. The predictive power of the inferred learning soil moisture algorithm did well with a mean absolute error of 0.054 over an airborne L-band retrieved surface over the same region.

Turbulent flows over and within forest canopies have recently been modeled with success using Large Eddy Simulations (LES). Validation exercises against experimental data suggest that models can be applied with a high degree of confidence for many applications, mechanical and physiological plant/atmosphere interaction analysis, seed or pollen dispersal, wildfire spread and firebrand transport, or investigation of causes of eddy-covariance technique bias. Long distances required for shear-induced turbulence to equilibrate, result in the widespread use of cyclic boundary conditions in LES atmospheric boundary layer studies. Vegetation drag dissipates air momentum in the atmosphere, but equilibrium is often achieved through compensatory momentum source, supplied by macro-scale pressure gradient forcing. Unfortunately, both classical Ekman balance or simple spatially-constant pressure gradient techniques for implementing this forcing have major drawbacks in the context of cyclic boundary conditions for the applications listed above. Among them, it is difficult to specify aspects of the mean velocity profile such as a specific desired wind velocity and direction at a reference height. In the present paper, we propose a new technique for capturing the effects of a large-scale pressure gradient force (LSPGF) that can be used at stand scale and enables simulation of realistic and specifiable wind fields. Several variants of this LSPGF are developed and analyzed here and validated against experimental data. Although this LSPGF technique is developed in the context of HIGRAD/FIRETEC wildfire simulations, LSPGF can be used for any LES wind modeling application aimed at generating detailed stand-scale wind fields with resolved turbulence and shear profiles consistent with vegetation structure in the boundary layer.

Field experiments were carried out during 2011-2014 at the Research and Experimental Center to Combating Desertification located in the Elsen Tasarkhai station of central Mongolia. The study was aimed to identify the effects of oxidized brown coal humic acid fertilizer on the relative growth rate of several trees for forest rehabilitation. The trees used were Populus sibirica, Salix ledebouriana and Acer tataricum. The experiment was carried out with the concentrations of 2,000, 10,000 and 20,000 mg L-1 of humic acid fertilization treatments. The measurement of relative height growth rate (RHGR) was conducted for a period of 4 years. The treatments showed significant differences within humic fertilizer concentrations which differed depending on the species. Compared to the monthly RHGR over the study, the treatment of fertilizers were significantly better for tree growth. P. sibirica in the 10,000 and 20,000 mg L-1 humic acid fertilizers had significant height growth rates. In addition, when the humic acid treatments were compared to control, A. tataricum decreased over the years which were statistically significant for high growth rate and a positive effect of humic acid fertilization treatments was observed. Furthermore, results showed that oxidized brown coal humic acid fertilizers as organic fertilizer can have a positive effect for the growth of A. tataricum during the study years. The results showed that the soil chemical properties EC, CO2, NO3, and K2O were significant among all the treatments compared to the control. The effect on P2O5 statistically significantly increased among all the treatments. However, pH and Mg were not significant effect among all the treatments. Combining the results obtained from the oxidized brown coal humic acid fertilization with sustainable land management practices can help improve soil organics for environmental issues in degraded sandy soil regions.

The aim of this work is to explain the behaviour of the multiresistance percentage of Pseudomona aeruginosa in some countries of Europe through a multivariate statistical analysis and machine learning validation, using data from the European Antimicrobial Resistance Surveillance System, the World Health Organization and the World Bank. First, we will use a descriptive analysis and a principal components analysis. Then, we use a k-means clustering to determine the countries and regions that are most affected by the antibiotic resistance. Second, we expand the database by adding some socioeconomic, governance and antibiotic-consumption variables. We then run a data panel regression analysis to determine some functions that relates the multiresistance percentage with those new variables. Finally, we use machine learning techniques to validate a pooling panel data case, using XGBoost and random forest algorithms. The results of the data panel analysis indicate that the most important variables for the multiresistance percentage are corruption control and the rule of law. Similar results are found with the machine learning validation analysis, where the human development index is an additional important variable for the multiresistance percentage.

Wearable devices have become ubiquitous, collecting rich temporal data that offers valuable insights into human activities, health monitoring, and behavior analysis. Leveraging this data, researchers have developed innovative approaches to classify and predict time-based patterns and events in human life. Time-based techniques allow the capture of intricate temporal dependencies, which is the nature of the data coming from wearable devices. This paper focuses on predicting well-being factors, such as stress, anxiety, positive and negative affect, on the Tesserae dataset collected from office workers. We examine the performance of different methodologies, including deep learning architectures, LSTM, ensemble techniques, Random Forest (RF) and XGBoost and compare their performances for time-based and non-time-based versions. In time-based versions, we investigate the effect of previous records of well-being factors on the upcoming ones. The overall results show that time-based LSTM performs the best among conventional (non-time-based) RF, XGBoost, and LSTM. The performance even increases when we consider a more extended previous period, in this case, 3 past-days rather than 1 past-day to predict the next day. Furthermore, we explore the corresponding biomarkers for each well-being factor using feature ranking. The obtained rankings are compatible with the psychological literature. In this work, we validated them based on device measurements rather than subjective survey responses.

Subcortical beetles interact with a wide range of semiochemicals released from different sources, including trees, fungi, and insect pheromones. While the attraction of bark beetles, their insect predators, and competitors to bark beetle pheromones is well-studied, the attraction of these beetle communities to other sources of semiochemicals remains poorly understood. We tested the attraction of bark and wood-boring beetles and their predators to host stress volatiles, fungal volatiles, and a mountain pine beetle lure in the field. Host stress volatiles were derived from lodgepole pine trees stressed by three fungal symbionts of mountain pine beetle and two common phytopathogens. Our results showed that bark beetles, particularly mountain pine beetles, show a preference for a combination of fungal volatiles, particularly 2-methyl-1-butanol and mountain pine beetle lures. Without the addition of lures, 2-methyl-1-butanol was also identified as a key fungal volatile in the attraction of mountain pine beetle competitors from the Cerambycidae and Buprestidae families. Predators in the Elateridae and Staphylinidae families showed attraction to host stress volatiles and the healthy tree volatile profile. These findings suggest that these chemicals warrant further field testing for potential use in monitoring and management of subcortical beetle populations.

Machine learning (ML) has a large capacity to learn and analyze a large volume of data. This study aimed to train different algorithms to discriminate between healthy and pathologic corneal images by evaluating digitally processed spectral-domain optical coherence tomography (SD-OCT) corneal images. A set of 22 SD-OCT images belonging to a random set of corneal pathologies was compared to 71 healthy corneas (control group). A binary classification method was applied; three approaches of ML were used. Once all images were analyzed, representative areas from every digital image were also processed and analyzed for a statistical feature comparison between healthy and pathologic corneas. The best performance was obtained from transfer learning - support vector machine (TL-SVM) (AUROC = 0.94, SPE 88%, SEN 100%) and transfer learning – random forest (TL- RF) method (AUROC = 0.92, SPE 84%, SEN 100%), followed by convolutional neural network (CNN) (AUROC = 0.84, SPE 77%, SEN 91%) and random forest (AUROC = 0.77, SPE 60%, SEN 95%). The highest diagnostic accuracy in classifying corneal images was achieved with the TL-SVM and the TL-RF models. In image classification, CNN was a strong predictor. This pilot experimental study developed a systematic mechanized system to discern pathologic from healthy corneas.

Sour waters are one of the main aqueous byproducts generated during petroleum refining and require processing in Sour Water Treatment Units (SWTUs) to remove contaminants such as H₂S and NH₃ in compliance with environmental legislations. Therefore, monitoring the composition of SWTU effluents, including acid gas, ammoniacal gas, and treated water, is essential. This study aims to present an AI (artificial intelligence) hybrid-based methodology to develop soft sensors capable of real-time prediction of H₂S and NH₃ mass fractions in the effluents of SWTUs and validate them using real data from industrial units. Initially, a new database based on the dynamic simulation of a two stripping columns SWTU phenomenological model, developed in Aspen Plus Dynamics® V10, was generated, aiming at non-faulty runs, unlike our previous work [1]. Ensemble methods (Decision Trees), such as Gradient Boosting and Random Forest, and Support Vector Machines were compared for soft sensor creation using these simulated data. The best outcome was the development of six soft sensors based on Random Forest with R² greater than 0.87, MAE less than 0.12, MSE less than 0.17, and RMSE less than 0.41. Variable importance analysis revealed that the temperature of the second stage of Column 1 significantly influences the thermodynamic equilibrium of H₂S and NH₃ separation from sour waters, being critical for five of the six soft sensors. After this initial stage using data from the phenomenological model, data from an industrial-scale SWTU were used to develop real soft sensors. The results proved the effectiveness of the conjugated use of physical model and industrial data approach in the development of soft sensor for two-column SWTUs.

Tree-killing bark beetles are the most economically important insects in conifer forests worldwide. Yet despite >200 years of research, the drivers of population eruptions or crashes are still not fully understood, precluding reliable predictions of the effects of global change on beetle population dynamics and impacts on ecosystems and humans. We critically analyze potential biotic and abiotic drivers of population dynamics of the European spruce bark beetle (Ips typographus) and present a novel ecological framework that integrates the multiple drivers governing this bark beetle system. We call for large-scale collaborative research efforts to improve our understanding of the population dynamics of this important pest; an approach that might serve as a blueprint for other eruptive forest insects.

The concept of ecosystem services (ESs) provides a valuable approach to communicate societies' dependence on natural ecosystems, assisting in the evaluation of measures to protect vegetation in watersheds that promote water-related ESs. Vegetation cover and land use are important factors related to the capacity of ecosystems to provide soil loss regulation and sediment retention services, which are highly relevant for sediment management in watersheds draining into reservoirs with multiple water uses. This study aims to assess the relationship between potential changes in land use and land cover and the sediment retention service provided by riparian vegetation in a watershed draining into a hydroelectric reservoir in the Brazilian Cerrado. Sediment load was selected as a physical variable that affects different water uses in reservoirs, with these uses being dependent on the quality or quantity of stored water. Scenarios were analyzed to represent landscape reconfigurations from a baseline condition in order to account for the recovery of riparian vegetation by the agricultural sector, as foreseen in the Brazilian Forest Code. To map and quantify variations in annual sediment retention, the InVEST model was used, which allows estimating an integrated response of the drainage basin to large-scale land use changes over time and space. The results show that for the drainage basin of the Corumbá IV Hydroelectric Power Plant (HPP), the recovery of riparian areas occupied by annual crops has the potential to generate greater benefits to water use in the reservoir. In the studied catchment area, 14% of the total vegetation deficit in riparian areas is occupied by crops, while 86% is occupied by pastures. This highlights the buffering role of riparian vegetation as an effective practice for managing sediment flows originating from sheet erosion in agricultural landscapes. The methodology employed in this study allows for the quantification and mapping of the effects of soil and water conservation measures in river basins. This enables the prioritization of sectoral efforts for the restoration of native vegetation, considering the highest returns in benefits perceived by water users affected by sediment input in reservoirs. The study's results reinforce the importance of conserving vegetation in riparian areas and their surroundings for sediment retention, highlighting the role of these areas as assets in providing water-related ecosystem services.

1) Background: Climate change may subject forests to climate conditions to which they are not adapted. Elevated temperatures reduce net photosynthesis by increasing respiration rates and increasingly long droughts dramatically increase morbidity. CO₂ enrichment enhances productivity, but it is not clear to what extent CO₂ enrichment can offset the negative effects of elevated temperatures and longer droughts. 2) Methods: We used a mechanistic landscape model to conduct controlled simulation experiments manipulating CO₂ concentration, temperature, drought length and soil water capacity. 3) Results: We found that elevated CO₂ stimulates productivity such that it dwarfs the negative effect caused by elevated temperature. Energy reserves were not as strongly mitigated by elevated CO₂, and mortality of less competitive cohorts increased. Drought length had a surprisingly small effect on productivity measures, but had a marked negative effect on mortality risk. 4) Conclusions: Elevated CO₂ compensated for the negative effect of longer droughts in terms of productivity measures, but not survival measures.

Accurate detection of forest restoration sites using deep learning is crucial for effective ecosystem management, optimizing reforestation efforts, and ensuring environmental sustainability. While various deep learning-based systems have been developed for this purpose, the influence of different neural network architectures on model performance during the identification of forest restoration sites remains underexplored. This study aimed to address this gap by exploring the optimal methodology for extracting and classifying candidate sites for forest restoration based on Convolutional Neural Networks (CNNs), specialized for image recognition. Four categories—arable land, road and barren, quarry, and forest—were defined as candidate sites for forest restoration. A dataset comprising 17,043 samples was divided into training (11,929) and validation (5,114) sets at a ratio of 7:3 for model learning. Model accuracy was evaluated using pixel accuracy (PA) and mean intersection over union (mean IoU). The Resnet152-U-Net model demonstrated a pixel accuracy of 95.2% and a mean IoU of 61.3%, indicating excellent performance in extracting candidate sites for forest restoration. This approach offers spatial and temporal advantages over conventional field surveys or aerial image-based assessments, potentially serving as valuable data for selecting future forest restoration sites.

In recent decades, large-scale forest disturbances such as windthrow and bark beetle infestations have significantly impacted the carbon balance of Earth and forest ecosystems, mainly by altering soil respiration (SR) in addition to decreased gross primary productivity. SR is considered the second highest flux on Earth, emitting 78-98 Gt C yr-1 to the atmosphere, thus contributing to global warming. Post-disturbance development is marked by changes in the size of SR. To investigate the impact of bark beetle (Ips typographus) infestations in mountain spruce forests on SR, we measured SR at infested sites by bark beetles and adjacent undisturbed stands in the High Tatra Mountains (Slovakia). The measurements were conducted during the vegetation period (May-September) in 2016 and 2017, five to six years after the initial attack by bark beetles, at an altitudinal gradient (1100-1400 m a.s.l.). SR varied throughout different months and altitudes, and we observed that SR at infested sites reached higher values (in most cases) than at uninfested stands. Average monthly and altitude SR rates during both vegetation periods showed higher values at infested sites, but not all of them were statistically significant. We observed an insignificant change in SR rate between 2016 and 2017 at both infested and uninfested sites. The highest rates of SR were observed in 2016 from July to August at both infested and undisturbed sites. On the other hand, in 2017 the highest SR rates were observed in June and July at undisturbed sites and from June to August at infested sites. However, yearly SR from May-September at infested sites showed significantly higher rates than uninfested ones in both years. SR showed a decreasing pattern with elevation gain in 2016 at infested sites. However, this pattern was not observed in 2017. Based on our observation and results we postulate that SR rates at infested sites are boosted by needle fall and debris from dead and dying trees, which increases heterotrophic SR and compensates the decrease of autotrophic SR from tree roots. This study provides important insights into the impact of bark beetle infestations on SR and highlights the need for further research on the long-term effects of forest disturbances on carbon cycling.

This article presents a comparative analysis of three Machine Learning models, namely Logistic Regression, Decision Tree Classifier, and Random Forest Classifier, for prostate cancer detection. The models were trained and evaluated using clinical data, and their performance was assessed using various evaluation metrics. The results show that Logistic Regression achieved the highest accuracy (90%) among the three models, followed by Random Forest Classifier (76.67%) and Decision Tree Classifier (73.33%). Similarly, Logistic Regression demonstrated superior precision (95.65%) and F1 Score (93.62%), indicating its effectiveness in identifying true positive cases. However, the Decision Tree Classifier exhibited higher recall for the negative class (83.33%) compared to the positive class (70.83%), while Random Forest Classifier showed balanced recall for both classes (66.67% for negative and 79.17% for positive). These findings suggest that Logistic Regression outperforms the other models in terms of accuracy and precision, while the Decision Tree Classifier and Random Forest Classifier provide better recall for certain classes. The results highlight the potential of Machine Learning in prostate cancer detection and provide insights for further research and improvement of the models.

Land Surface Temperature (LST) is significant for climatological and environmental studies. LST products from satellites, however, suffer from the tradeoff between spatial and temporal resolution. Spatial downscaling has emerged as a well explored field aiming to overcome limitations arising from this tradeoff. Previous research on regression based LST downscaling models focused on utilizing predictors derived from optical imagery. Weather-dependency of optical imagery data, however, can influence downscaling models by the weather conditions. To cope this issue, in this study, we involve predictors derived from the weather-independent Sentinel-1 Synthetic Aperture Radar (SAR) imagery to downscale Landsat-8 LST data. In this context, we propose to use machine learning techniques, namely Random Forest (RF) and Convolutional Neural Networks (CNN). To demonstrate the applicability and performance of the proposed method, extensive experimental analyses were conducted over Zuid-Holland in the Netherlands. From the experiments, we found that the results obtained with radar predictors were comparable to those achieved using optical predictors. This confirms that the proposed method indeed paves a new way for mapping land surface temperature using SAR images.

Plant roots have significant effects on the soil erosion rates, since they can strongly change the soil detachment capacity (Dc). This study quantifies Dc at different flow rates in soils with Alnus subcordata species, compared to three other species (Brachythecium plumose, Gleditsia caspica and Sambucus ebulus species) in the Saravan forest park and develops regression equations for predicting Dc. Undisturbed samples collected from soils with the four tree species and subjected to five slopes (from 4.3 to 38.3%) and five water discharges (from 0.28 to 0.71 l m−1 s−1) using a hydraulic flume. The results showed that Dc was significantly lower in soils with Alnus subcordata species compared to Brachythecium plumose, Gleditsia caspica and Sambucus ebulus species, as the consequence of the changes in the root characteristics, so that Dc was negatively correlated with root weight density, root length and root biomass. The unit stream power had high accuracy for predicting Dc for all of the studied species. The lowest value of rill erodibility (Kr) was obtained in soils with Alnus subcordata species using regression relationship between the Dc and the shear stress of the soil. This experiment helped to show the importance of plant roots in reducing the soil detachment rates and provided a contribution in understanding the choice of appropriate species for soil conservation.

Species diversity has been shown to be influenced by environmental factors, but the mechanism underlying their relationship remains unclear across spatial scales. Based on field investigation data collected from 3,077 sample plots in temperate forest ecosystems, we compared tree species richness, evenness and dominance at 10 km × 10 km, 30 km × 30 km and 90 km × 90 km spatial scales. Then, we detected the scale dependence of changes in tree species composition on climate, topography and forest structure using variation partitioning and quantified their contribution to tree diversity with gradient boosted models (GBMs) and fitted their relationships. The magnitude of tree richness, evenness and dominance significantly increased with spatial scale. Ecological factors jointly accounted for 24.3%, 26.5% and 38.5% of the variation in tree species composition at the three spatial scales, respectively. Annual mean temperature had a strong impact on tree richness, evenness and dominance and peaked at an intermediate scale. Tree evenness and dominance increased with the variation of temperature but had upper and lower limits. Tree richness obviously increased with annual precipitation on multiple scales and decreased with annual sunshine duration at large spatial scale. Tree richness, evenness and dominance obviously increased with the variation elevation and diameter at breast height at large scales and small scales, respectively. Tree dominance decreased with tree height in a hump at small scale. The dependence of tree diversity on ecological factors increased with spatial scales. Furthermore, different factors exert various controls on tree diversity at different spatial scales, representing a comprehensive mechanism regulating tree diversity.

Payments for Ecosystem Services are a voluntary market-based instrument to remunerate provider(s) of ecosystem services by those who benefit from them. Our research aimed to create an ex-post evaluation framework to identify bottlenecks and elements hindering the success of a solution-driven PES scheme. The framework was applied to a case study to test its feasibility and concerns the provision of health and recreational services in the Medvednica Nature Park (Zagreb, Croatia). The framework was set up through three main sources: the study of PES implementation project documentation, semi-structured interviews with visitors and key stakeholders and web-scraping of TripAdvisor reviews of the park. The main findings confirmed society's interest in the park, but the lack of mapping, quantification, economic valuation and accounting of the services analysed, society's little or no demand to pay for their provision and confused knowledge of the property rights of some ecosystem service providers in the area limit the success of the PES scheme. The framework was useful to describe the chosen PES scheme and to identify bottlenecks and fragilities of the system in place, allowing to correct its application flaws and, on the other hand, to demonstrate its replicability in other contexts.

This study aimed to investigate the possibility of using one-shot hyperspectral airborne images to recognize crops for an area with many small plots. The results showed that unsupervised clustering methods could classify crops with an accuracy of 80%, which improved to 90% when restricted to only grain crops, using a single airborne hyperspectral recording. However, additional layers such as NDVI, DTM, slope, and aspect did not improve classification accuracy. For comparison, the accuracy of clustering time series Sentinel-2 images with NDVI layers and DTM-derived data yielded an accuracy of: 74% ,Sentinel-2 time series 68% and single one registration before harvest - 39%. The results of the random forest classification were slightly less accurate due to a lack of sufficient reference data. However, it is challenging to verify the reported accuracy of crop recognition in the literature above 90% due to differences in analysis methodologies, reference data selection, pixel/object approaches, metric choice, and calculation formulas used.

Despite the abundance of tree diversity in the natural world, and generally high tree species richness in urban areas, urban forests continue to be dominated by a limited number of species. As socio-ecological systems, urban forests are shaped by historical and current management efforts and decision-making of a wide range of human actors. Drawing on past research, we offer a conceptual framework for describing the complex interactions among tree producers and consumers as trees are selected, grown, specified, and planted in private and public urban areas. We illustrate how multiple layers of selection criteria filter down the entirety of potential local tree diversity to a handful of commonly used and accepted tree species. We detail the actors and decision makers who impact tree composition and diversity across several land types. Finally, we identify research, education and outreach needs as they relate to creating more diverse and resilient urban forest ecosystems.

Photovoltaic power generation has high variability and uncertainty because it is affected by uncertain factors such as weather conditions. Therefore, probabilistic forecasting is useful for optimal operation and risk hedging in power systems with large amounts of photovoltaic power generation. However, deterministic forecasting is the mainstay of photovoltaic generation forecasting; there are few studies on probabilistic forecasting and feature selection from weather or time-oriented features in such forecasting. In this study, prediction intervals were generated by the lower upper bound estimation using neural networks with two outputs to make probabilistic predictions. The objective was to improve prediction interval coverage probability (PICP), mean prediction interval width (MPIW), and loss, which is the integration of these two metrics, by removing unnecessary features through feature selection. When features with high gain were selected by random forests (RF), in the forecast of 14.7-kW PV systems, loss improved by 1.57 kW, PICP by 0.057, and MPIW by 0.12 kW on average over two weeks compared to the case where all features were used without feature selection. Therefore, the low gain features from RF act as noise in LUBE and reduce the prediction accuracy.

Immersion in forest environments was shown to produce beneficial effects to human health, in particular psychophysical relaxation, so much that this practice is increasingly recognized as a form of integrative medicine. Limited evidence exists about both statistical significance and size of the effects conditioned on personal characteristics, as well as on the main external variables. The primary purpose of this study was to substantiate the very concept of forest therapy by means of the quantification and significance of the psychological effects, stratified by gender, age groups and place of residence. A preliminary qualitative analysis of the main determinants, in particular the method of conducting, the meteorological comfort and the concentration of volatile organic compounds in the forest atmosphere, was afforded. Seven forest therapy sessions were performed in late summer though early fall, resulting in 150 psychological self-assessment questionnaires administered before and after each session. The results were comparable or even better than others reported in the international literature. Moreover, preliminary evidence arose about different functionality towards specific psychological indexes conditioned at least on gender and age groups, as well as meteorological comfort, structured programs and, possibly, volatile organic compounds showed an impact on the outcomes.

ClinVar is a web platform that stores around 774k curated entries, which allows exploring genetic variants and their associations with complex phenotypes. A partial set of ClinVar’s genetic associations were reported with conflict of interpretation or uncertain clinical impact significance, which currently challenges clinicians and geneticists. Here, we evaluate the performance of data pre-processing methods combined with classical prediction methods, such as Naive Bayes, Random Forest, and Support Vector Machine to build a meta-prediction model aiming to improve genetic pathogenicity interpretation. Models were trained with ClinVar data (September 2020), and genetic variants were annotated with eight functional impact predictors catalogued with SnpEff/SnpSift (v4.3). A 10-fold cross-validation strategy was performed for evaluation by accuracy, F1-Score, Receiver Operating Characteristic, Area Under Curve. The best meta-prediction model raises by combining one-hot encoding with tree-based classifiers as Random Forest, which shows Area Under Curve ≥ 0,93. We predict pathogenicity for 109k genetic variants, which were found labeled as uncertain significance or conflict of interpretation. Additionally, we implemented AmazonForest (https://www.lghm.ufpa.br/amazonforest), a web tool to query data for a set of 5k variants that were predicted with high pathogenic probability (RFprob >= 0.9).

The research objectives was to determine the plants vegetation profile in forest revegetation and Mount Arjuna springs. The method used was descriptive method. While based on the techniques and tools used to research, the author uses the survey method to obtain facts that occur in the research area, namely in the area around the springs of Arjuna mount, Pasuruan, East Java, Indonesia. Data obtained in the field are then processed and analyzed using GIS, ArcView 3.3 and Google Earth programs. The results of the study explain the profile of plant vegetation, namely plant stratification, bird wealth, taxonomic wealth and plant density have a significant effect on forest revegetation and springs in Arjuna mount. The forest vegetation profile has a positive and significant effect on the preservation of springs. The better the profile of forest vegetation, the preservation of springs will be better, and vice versa.

Remote sensing technologies may play a fundamental role in the environmental assessment of open-cast mining and the accurate quantification of mine land rehabilitation efforts. Here, we developed a systematic geographic object-based image analysis (GEOBIA) approach to map the amount of revegetated area and to quantify the land-use changes in open-cast mines in the Carajás region situated in the eastern Amazon. Based on high-resolution satellite images from 2011 to 2015 from different sensors (GeoEye, WorldView-3 and Ikonos), we quantified forests, cangas (natural metalliferous savanna ecosystems), mine land, revegetated areas and water bodies. Based on the GEOBIA approach, threshold values were established to discriminate land cover classes using spectral bands, and the NDVI and NDWI indices and LiDAR digital ground and slope models. The overall accuracy was higher than 90%, and the Kappa indices varied between 0.82 and 0.88. During the observation period, the mining complex expanded; for that, canga and forest vegetation was converted to mine land. At the same time, the amount of revegetated area increased. Thus, we conclude that our approach is capable of providing consistent information regarding land cover changes in mines, with a special focus on the amount of revegetation necessary to fulfill environmental liabilities.

The study was conducted in coniferous and deciduous old growth forests in two forest complexes located in: i) the fenced area of the Popielno Research Station of the Polish Academy of Sciences, with free-living Polish pony [Polish primitive horse (Equus ferus caballus)], and ii) open Maskulińskie Forest District managed (harvested) forest, without horses. The impact of forest animals on ground cover layer as well as on understory shrub layer and undergrowth, in i) area (horses and other forest animals) was compared with the results in ii) area (forest animals without horses). Very significant differences in the understory and undergrowth (above 0,5 m) layer vegetation communities structure between both areas and type of stands were found. The results suggest that the presence of the Polish horse substantially changed the species composition and increased the species diversity of the ground layer and shrub layer both on coniferous forest and in the deciduous forest habitats. The height of the shrub layer trees was lower by 30% in the area with the Polish horse.

Many agonists for the estrogen receptor are known to disrupt endocrine functioning. We have developed a computational model that predicts agonists for the estrogen receptor ligand-binding domain in an assay system. Our model was entered into the Tox21 Data Challenge 2014, a computational toxicology competition organized by the National Center for Advancing Translational Sciences. This competition aims to find high-performance predictive models for various adverse-outcome pathways, including the estrogen receptor. Our predictive model, which is based on the random forest method, delivered the best performance in its competition category. In the current study, the predictive performance of the random forest models was improved by strictly adjusting the hyperparameters to avoid overfitting. The random forest models were optimized from 4,000 descriptors simultaneously applied to 10,000 activity assay results for the estrogen receptor ligand-binding domain, which have been measured and compiled by Tox21. At this time, our model delivers the highest predictive power on estrogen receptor agonists in the world. Furthermore, analysis of the optimized model revealed some important features of the agonists, such as the number of hydroxyl groups in the molecules.

This study utilizes a combination of optical PlanetScope imagery and Synthetic Aperture Radar (SAR) data from Sentinel-1 to investigate land cover changes in Dili, Timor-Leste, following Tropical Cyclone Seroja. The primary objective is to evaluate how integrating these datasets enhances disaster monitoring and response in flood-affected areas. The Random Forest classifier, known for its robustness in handling high-dimensional and noisy data, was applied to classify land cover into six distinct classes: vegetation, water, built-up areas, bare soil, clouds, and shadows. The classification was performed across three phases—pre-disaster, post-disaster, and recovery—using Google Earth Engine (GEE). Binary segmentation using Otsu thresholding was applied to the SAR images to refine the classification by delineating water bodies from non-water areas. The study achieved high classification accuracy, with overall accuracy ranging from 97.2% to 98.7%, and the Kappa index, which measures agreement between classified and reference data, remained consistently strong, indicating reliable model performance. Key results include a significant increase in water bodies and extensive damage to vegetation and built-up areas during the post-disaster phase, followed by partial recovery in the subsequent period. Despite the high accuracy, urban areas posed classification challenges due to misclassification between built-up and bare soil categories. This research offers a methodological framework for integrating optical and SAR data with machine learning for land cover change detection in post-disaster scenarios. The societal benefits of this study include improved disaster preparedness, enhanced recovery planning, and valuable insights into flood impact mitigation in regions like Timor-Leste, where technical and data limitations persist.

This manuscript reviews three case studies from Brazil, Panama, and Portugal that illustrate Nature-based Solutions. The Tijuca Forest in Rio de Janeiro is a remarkable story of centuries of forest management that today is recognized as a UNESCO World Heritage Site. The Panama Canal Watershed produces water for Canal operations, electricity generation, and drinking water for half the country´s population. Traditional windmills and weirs near streams in the Alentejo Region, Portugal, have largely been abandoned due to the damming of the Guadiana River. Yet today, weirs are increasingly recognized for their important contribution to water provisioning in this dry region. All have a primary goal related to water provisioning, yet their ecosystem benefits are multiple. The cases offer important lessons for adaptation to climate change, cultural benefits from traditional human activities, and concerns about social equity.

Accurate agricultural commodity price models enable efficient allocation of limited natural resources, leading to improved sustainability in agriculture. Because of climate change, price volatility and uncertainty for the sector are expected to increase in the future, increasing the need for improved price modeling. With the emergence of machine learning (ML) algorithms, novel tools are now available to enhance the modeling of agricultural commodity prices. This research uses both univariate and multivariate ML techniques to perform probabilistic price prediction modelling for the Canadian beef industry, taking into account beef production, commodity market, and international trade features to enhance accuracy. We apply multivariate algorithms by using support vector regression (SVR), random forest (RF), and adaboost (AB) and univariate algorithms by using autoregressive integrated moving average (ARIMA), seasonal ARIMA (SARIMA), and the seasonal autoregressive integrated moving average with exogenous factors (SARIMAX). We apply these models to monthly fed steer price data between January 2005 and September 2023 and compare predicted prices with observed prices using several validation metrics. The outcomes indicate that both random forest (RF) and adaboost (AB) in multivariate modeling show superior performance in accurately predicting Alberta fed steer prices in comparison to other algorithms. To better account for the variance of the best model performance, we subsequently adopted a probabilistic approach by considering uncertainty in our best-selected ML model. The beef industry can use these improved price models to minimize resource waste and inefficiency in the sector and improve the long-term sustainability prospects for beef producers in Canada.

Power consumption prediction is a crucial component in enhancing the efficiency and sustainability of building operations. This study investigates the impact of data collection frequency and model selection on the predictive accuracy of power consumption in two distinct building types: an Academic one with 15-minute interval data and an Industrial one with hourly data. Various machine learning models, including Support Vector Machine (SVM) with Radial and Sigmoid kernels, Random Forest (RF), and Deep Neural Networks (DNN), across different data splits and feature sets. Our analysis reveals that higher data collection frequency generally improves model performance, as indicated by lower RMSE, MAPE, and CV values, alongside higher R² scores. The inclusion of more historical power consumption features has also been found to have a more significant impact on the accuracy of predictions than including climate condition features. Moreover, the SVM-Radial model consistently outperformed others, particularly in capturing complex, non-linear patterns in the data. However, the DNN model, while competent in some metrics, showed elevated MAPE values, suggesting potential overfitting issues. These findings suggest that careful consideration of data frequency, features and model selection is essential for optimizing power prediction, contributing to more efficient power management strategies in building operations.

Global climate change requires urgent solutions. Ambitious tree-planting initiatives, many already underway, aim to sequester enormous quantities of carbon, partly compensating for the anthropogenic CO₂ emissions that are a major cause of rising global temperatures. However, poorly planned and executed tree-planting could actually increase CO₂ emissions and have long-term, deleterious impacts on biodiversity, landscapes and livelihoods. Here, we highlight the main environmental risks of large-scale tree planting and propose ten golden rules, based on some of the most recent ecological research, to implement forest ecosystem restoration that maximizes rates of both carbon sequestration and biodiversity recovery, while simultaneously improving livelihoods. These are: i) Protect existing forest first; ii) Work together (involving all stakeholders); iii) Maximize biodiversity recovery to meet multiple goals; iv) Select appropriate areas; v) Use natural regeneration wherever possible; vi) Select species to maximise biodiversity; vii) Use resilient plant material (with appropriate genetic variability and provenance); viii) Plan ahead for infrastructure, capacity and seed supply; ix) Learn by doing (using an adaptive management approach); and x) Make it pay (ensuring the economic sustainability of the project). We focus on the design of long-term strategies to tackle the climate and biodiversity crises and support livelihood needs. We emphasize the role of local communities and their dependence on benefits from successful reforestation programmes that restore ecosystem functioning and deliver a diverse range of forest products and services. While there is no simple and universal recipe for forest restoration, it is now crucial to build on the public and private interest in this topic to ensure interventions provide effective, long-term carbon sinks and maximise benefits for biodiversity and people.

Objective: This study aims to construct an early risk warning model to predict the risk of treatment failure in patients undergoing sequential High-Flow Nasal Cannula (HFNC) oxygen therapy following mechanical ventilation weaning. Methods: A retrospective analysis was conducted on clinical data from 145 patients who received HFNC treatment in the Emergency Intensive Care Unit of the Third People's Hospital of Bengbu City from June 2018 to June 2023. A wide range of indicators including general information, comorbidities, laboratory test results, vital signs, disease-related scores, and oxygenation data were collected. Data analysis was performed using R software, starting with the Lasso regression to filter features related to treatment outcomes. Patients were divided into a training set (70%) and a validation set (30%) using random grouping software. The Random Forest algorithm was then employed to evaluate and rank the important features related to outcome indicators. The predictive efficiency and stability of the model were assessed through the Receiver Operating Characteristic (ROC) curve, calibration curve, and decision curve analysis, culminating in the construction of an early risk warning nomogram. Results: The study found that the Random Forest model exhibited high predictive accuracy in the training set (AUC=0.98) and good stability in the validation set (AUC=0.84). Key feature variables identified by the model, such as APACHE II score, BNP, NLR, mROX, and SOFA, were found to significantly impact the prediction of HFNC treatment failure. Based on these variables, an early warning nomogram was further developed, providing clinicians with a convenient and effective risk assessment tool. Conclusion: This study has constructed an early risk warning model based on the Random Forest algorithm, capable of effectively predicting the risk of HFNC treatment failure. The model's high predictive efficiency and stability offer strong support for clinical decision-making, contributing to personalized treatment and improved patient outcomes. Future research should aim to expand the sample size, perform multicenter validation, and explore the integration of the model into Clinical Decision Support Systems for real-time risk assessment and intervention.

In order to reduce the environmental impact of energy enterprises, it is important to promptly identify cases of possible changes in the quality of wastewater generated at power plants, that is cases of exceeding the maximum permissible concentrations of pollutants in wastewater. The goal of the method for detecting complex anomalies in multidimensional time series obtained from smart energy station’s sensor channels is to increase the accuracy of detecting pollution levels in industrial wastewater. To achieve this goal, the following tasks were solved: methods for detecting time series anomalies were analyzed, the method for detecting complex anomalies was developed, software implementation of the algorithm was carried out and experiments were conducted. The developed method is proposed to be used in an smart energy monitoring system.

Fraudulent transactions pose a significant threat to financial institutions and e-commerce platforms.Machine learning models, trained on historical labeled data (fraudulent vs. legitimate transactions), are often employed to identify and prevent fraud. However, real-world datasets frequently exhibit class imbalance, where fraudulent transactions (minority class) are significantly outnumbered by legitimate transactions (majority class). Machine learning models may perform poorly as a result of this imbalance, underestimating fraud and favouring the majority class. This paper proposes a novel approach to address class imbalance and improve fraud detection accuracy. We explore the implementation of FROST (Feature space RObust Synthetic saTuration) oversampling, a technique specifically designed to generate synthetic samples for the minority class. The FROST function leverages the k-nearest neighbors (KNN) algorithm and a user-defined amplification factor (m) to create synthetic data points that closely resemble existing minority class instances. We integrate the FROST-enhanced oversampling technique into the machine learning pipeline for fraud detection. The paper evaluates the effectiveness of this approach compared to traditional oversampling methods and analyzes its impact on classification accuracy metrics.

Fossil body parts of the two cold-adapted ground beetle species, Elaphrus lapponicus and Diacheila polita, were found from a deposit dated in the late Last Glacial period in Hokkaido, Japan. The paleoenvironment was estimated from their modern distribution and habitat, along with the results of the paleobotanical studies at the site. The temperature was at least 6 degrees lower than modern in summer, and the area around the site was mostly covered with forest tundra, which can currently be seen in areas further north of Hokkaido.

Prescriptions for fuels management are universally applied across forest types in British Columbia, Canada, to reduce fire behaviour potential in the wildland-urban interface. Fuel thinning treatments are assumed to reduce the potential for sustained ignition and crown fire initiation by reducing surface fuel loading. We hypothesized that these prescriptions are not appropriate for the coastal wet forests in the Whistler region of the province. Our study measured the efficacy of fuel thinning treatments in four stands located in the Whistler community forest. We examined several in-stand microclimate variables during snow melt in the spring and at the height of fire danger in late summer, at thinned and unthinned locations paired using GIS- analysis. We found that thinning increased the wildfire risk based on the differences between unthinned and thinned areas in the same forest stand.

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. Two classification algorithms, support vector machine and random forest, were tested and gave very similar results. The percentage of correctly classified pixels was over 88% in both cases. The developed workflow relies 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. This land cover map is key input data for permafrost modeling, and hence for the quantification of climate change impacts in the studied area.

Nowadays, there is extensive production and use of plastic materials for different industrial activities. These plastics, either from their primary production sources or through degradation processes of the plastics themselves, can contaminate the ecosystem with micro and nanoplastics. Once in the aquatic environment, these microplastics can be the basis for the adsorption of chemical pollutants, favoring that these chemical pollutants disperse more quickly in the environment and can affect living beings. Due to the lack of information on adsorption, three machine learning models (random forest, support vector machine, and artificial neural network) to predict different microplastic/water partition coefficients (log Kd) were developed using two different approximations (based on the number of input variables). The best-selected machine learning models present, in general, correlation coefficients upper than 0.92 in the query phase, which indicate that these type of models could be used for a rapid estimation of the absorption of organic contaminants on microplastics.

The long-term resilience of Pyrenean forests in the face of historical anthropogenic clearing remains largely unknown. The palynological study of the varved sediments from a mid-elevation (1027 m) karstic lake provides a high-resolution record of three major century-scale deforestation/recovery (DR) cycles that occurred in the last two millennia, during Roman, Medieval and Modern times. Each DR cycle is characterized considering three different levels: overall forest trends, by forest type and by individual taxa. Overall, the studied forests exhibited high resilience, as they recovered almost completely after each deforestation event (bulk resilience). The critical point of no return (tipping point) beyond which forests would have irreversibly disappeared from the region was never reached, even after deforestation magnitudes above 60%. The different forest types identified (conifer, sclerophyll and deciduous) persisted over time, showing similar heterogeneous patterns with minor spatial reorganizations (mosaic resilience). Individually, the main forest taxa underwent minor variations in their relative abundances, always within the same attraction domains (community resilience). The high levels of resilience documented in these Pyrenean forests are attributed to the action of metapopulation and metacommunity processes and mechanisms in a highly dynamic patchy environment. Conservation actions should be focused on the maintenance of these spatial patterns and the associated ecological dynamics.

Non-woody forest products play a vital role in the economic uplifts of the local communities living in forest areas. This study was conducted in the Shishikoh Valley, district Chital to identify the economic importance of the Chilghoza nuts. The study was based on interviews and questionnaires, and a total of 50 questionnaires were collected from the whole valley. The results showed that before 2003, the people were unaware of the high economic value of the Chilghoza nuts, they used to sell the Chilghoza nuts at a very low price (US$ 1.7 to 2.4 per bag: approximately 5 Kg) and harvest it for fuelwood purposes. After the IPRP interventions, training and awareness, the local people started conservation of Chilghoza trees and sustainable cone harvesting. The total collection and sell out of Chilghoza nuts in the Shishikoh valley jumped to 87.9 tons and US$ 7.64/kg in 2005 from 32.7 tons and US$ 0.34-0.48/kg, respectively. This study concludes that IPRP interventions improved the economic values of Chilghoza nuts as well as the living standards of the local people.

Fossil-based emissions can be avoided through using wood in place of non-renewable raw materials as energy and materials. However, increasing wood harvest influences forest carbon stocks. This effect may reduce the overall climate benefit of wood use significantly but is widely overlooked. We carried out a systematic review of simulation studies and compared differences in forest carbon and amount of wood harvested between more and less intensive wood harvest scenarios for three different time perspectives; short (1-30 years), mid (31-70 years) and long (71-100 years). Out of more than 450 reviewed studies 44 provided adequate data. Our results show that increased harvesting reduced carbon stocks over 100 years in temperate and boreal forests roughly 1.6 (stdev 0.9) t_C per t_C harvested. The value proved to be robust when outliers explicitly influenced by other factors than change in harvest rate, such as increase in fertilization or forest area, were removed. Interestingly, no significant difference in carbon impacts was found for average values of boreal and temperate forests or between short and long time-horizons. However, impacts tend to be greatest in the mid-term. This carbon balance indicator that we estimated can be interpreted as carbon debit of wood harvest in forests. It is significant compared with the typical GHG credits in technosphere generated by avoiding fossil emissions in substitution and increase in carbon storage in harvested wood products, and should not be ignored. Our estimates provide default values that can directly be included in GHG balances of products or assessment of mitigation policies and measures related to wood use. However, more systematic scenarios and transparent data in which different factors influencing forest carbon stocks are separately studied are clearly required to provide better constrained estimates for specific forest types.

The construction of sustainable urban forests follows the principle that well-being in people is promoted when exposed to tree population. Facial expression is the direct representation of inner emotion that can be used to assess real-time perception in urban forests. The emergence and change of facial expressions for forest visitors are in an implicit process. The reserved character of oriental races strengthens the requirement for the accuracy to recognize expressions through instrument rating. In this study, a dataset was established with 2,886 randomly photographed faces from visitors in a constructed urban forest park and a promenade at summertime in Shenyang City at Northeast China. Six experts were invited to choose 160 photos in total with 20 images representing one of eight typical expressions as angry, contempt, disgusted, happy, neutral, sad, scared, and surprised emotions. The FireFACE ver. 3.0 software was used to test hit-ratio validation as the accuracy (ac.) to match machine-recognized photos with those identified by experts. According to Kruskal-Wallis test on the difference from averaged scores in 20 recently published papers, contempt (ac.=0.40%, P=0.0038) and scared (ac.=25.23%, P=0.0018) expressions cannot pass the validation test. Therefore, the FireFACE can be used as an instrument to analyze facial expression from oriental people in urban forests but contempt and scared expressions cannot be identified.

Trees in residential landscapes provide many benefits, but can injure persons and damage property when they fail. In hurricane-prone regions like Florida, USA, the regular occurrence of hurricanes has provided an opportunity to assess factors that influence the likelihood of wind-induced tree failure and develop species failure profiles. We assessed open-grown trees in Naples, Florida, following the passage of Hurricane Irma in September 2017 to determine the effect of relevant factors on the degree of damage sustained by individual trees. Of 4,034 assessed individuals (n = 15 species), 74% sustained no damage, 4% sustained only minor damage (i.e., minimal corrective pruning needed), 6% sustained significant damage (i.e., major corrective pruning needed), and 15% were whole tree failures (i.e., overturned trees or trees requiring removal). The proportion of individuals in each damage category varied among species, stem diameter at 1.4 m above ground, and the presence of utility lines, which was a proxy for maintenance. We compared our results with the findings of seven previous hurricanes in the region to explore species’ resilience in hurricanes.

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

This paper proposes an Integrated Fire Management (IFM) framework that can be used to support communities and resource managers in finding effective and efficient approaches to prevent damaging fires, as well as maintain desirable fire regimes in Kenya. Designing and implementing an IFM approach in Kenya calls for a systematic understanding of the various uses of fire and the underlying perceptions and traditional ecological knowledge of the local people. The here proposed IFM framework allows an evaluation of the risks posed by fires, while balancing them with their beneficial ecological and economic effects, and thus developing effective fire management approaches. A case study of the proposed IFM framework was conducted in Gathiuru Forest that is part of the larger Mt. Kenya Forest Ecosystem. Focus group discussions were held with key resource persons, primary and secondary data on socio-economic activities were studied, fire and weather records were analyzed and the current fire management plans were consulted. Questionnaires were used to assess how the IFM is implemented in the Gathiuru Forest Station. The results show that the proposed IFM framework is scalable and can be applied in places with fire-dependent ecosystems as well as in places with fire-sensitive ecosystems in Kenya. The effectiveness is dependent on the active participation, formulation and implementation of the IFM activities by the main stakeholder groups (Kenya Forest Service (KFS), Kenya Wildlife Service (KWS), and the Community Forest Associations (CFA)). The proposed IFM framework helps in implementing cost-effective approaches to prevent damaging fires and maintain desirable fire regimes in Kenya.

The productivity of forests is often considered to be limited by the availability of phosphorus (P). Knowledge of the role of organic and inorganic P in humid subtropical forest soils is lacking. In this study, we used chemical fractionation and 31P nuclear magnetic resonance (NMR) spectroscopy to characterize the form of P and its distribution in undisturbed perhumid Chamaecyparis forest soils. The toposequence of transects was investigated for the humic layer from summit to footslope and lakeshore. The clay layer combined with a placic-like horizon in the subsoil may affect the distribution of soil P because both total P and organic P (Po) contents in all studied soils decreased with soil depth. In addition, Po content was negatively correlated with soil crystalline Fe oxide content, whereas inorganic P (Pi) content was positively correlated with soil crystalline Fe oxide content and slightly increased with soil depth. Thus, Pi may be mostly adsorbed by soil crystalline Fe oxides in the soils. Among all extractable P fractions, the NaOH-Po fraction appeared to be the major component, followed by NaHCO3-Po; the resin-P and HCl-Pi fractions were lowest. In addition, we found no typical trend for Pi and Po contents in soils with topographical change among the three sites. From the 31P-NMR spectra, the dominant Po form in soils from all study sites was monoesters with similar spectra. The 31P-NMR findings were basically consistent with those from chemical extraction. Soil formation processes may be the critical factor affecting the distribution of soil P. High precipitation and year-round high humidity may be important in the differentiation of the P species in this landscape.

The presented study demonstrates the bi-sensor approach suitable for rapid and precise up-to-date mapping of forest canopy gaps for the larger spatial extent. The approach makes use of UAV RGB images on smaller areas for highly precise forest canopy mask creation. Sentinel-2 was used as a scaling platform for transferring information from UAV to a wider spatial extent. The various approaches of the improvement of the predictive performance were examined: (I) the highest R2 of the single satellite index was up to 0.57, (II) the highest R2 using multiple features obtained from the single date, S-2 image was 0.624 and, (III) the highest R2 on the multi-temporal set of S-2 images, was 0.697. Satellite indices such as ARVI, IPVI, NDI45, PSSRa, MCARI, CI, RI, and NDTI were the dominant predictors in most of the ML algorithms. The more complex ML algorithms such as SVM, Random Forest, GBM, XGBoost, and Catboost that provided the best performance on the training set exhibited weaker generalization capabilities. Therefore, a simpler and more robust Elastic Net algorithm was chosen for the final map creation.

As digitalization expands across all sectors, the economic toll of software defects on the U.S. economy reaches up to $2.41 trillion annually. High-profile incidents like the Boeing 787-Max 8 crash have shown the devastating potential of these defects, highlighting the critical importance of software testing within quality assurance frameworks. However, due to its complexity and resource intensity, the exhaustive nature of comprehensive testing often surpasses budget constraints. This research utilizes a machine learning (ML) model to enhance software testing decisions by pinpointing areas most susceptible to defects and optimizing scarce resource allocation. Previous studies have shown promising results using cost-sensitive training to refine ML models, improving predictive accuracy by reducing false negatives through addressing class imbalances in defect prediction datasets. This approach facilitates more targeted and effective testing efforts. Nevertheless, the generalizability of these models across different projects (cross-project) and programming languages (cross-language) remained untested. This study validates the model's applicability across diverse development environments by integrating various datasets from distinct projects into a unified, using a more interpretable ML approach. The results demonstrate that ML can support software testing decisions, enabling teams to identify up to seven times more defective modules with the same testing effort as a benchmark.