The early-season area estimation of the winter wheat crop as a strategic product is important for decision makers. Classification of multi-temporal images is an approach which is affected by many factors like appropriate training sample size, proper frequency and acquisition times, vegetation indices (VIs) type, temporal gradient of spectral bands and VIs, appropriate classifier and missed values because of cloudy conditions. This paper addresses the impact of appropriate frequency and acquisition times and VIs type along with the spectral and VI gradient on random forest (RF) classifier when missed values exist in multi-temporal images. To investigate the appropriate temporal resolution for image acquisition, the study area was selected on an overlapping area between two LDCM paths. In our developed method, the miss values of cloudy bands for each pixel are retrieved by the mean of k-nearest ordinary pixels. Then the multi-temporal image analysis is performed by considering different scenarios provided by decision makers in terms of desired crop types that should be extracted at early-season in the study areas. The classification results obtained by the RF decrease by 1.6% when temporally missed values retrieved by the proposed method, which is an acceptable result. Moreover, the experimental results demonstrated that if temporal resolution of Landsat 8 increased to one week the classification task can be conducted earlier with almost better results in terms of OA and kappa. The impact of incorporating VIs along with the temporal gradients of spectral bands and VIs as new features in RF demonstrated that the OA and Kappa are improved 3.1% and 6.6%, respectively. Furthermore, the obtained result showed that if only one image from seasonal changes of crops is available, the temporal gradient of VIs and spectral bands play the main role to discriminate remarkably wheat from barley. The experiments also demonstrated that if both wheat and barley merge to a single class the crop area can be estimated two months earlier with 97.1 and 93.5 in terms of OA and kappa, respectively.

Understanding the dynamics of Organic Carbon mineralization is fundamental in forecasting biosphere to atmosphere Net Carbon Ecosystem Exchange (NEE). With this perspective, we developed 3D-CMCC-PSM, a new version of the hybrid Process Based Model 3D‐CMCC FEM where also heterotrophic respiration (R_h) is explicitly simulated. The aim was to quantify NEE as a forward problem, by subtracting Ecosystem Respiration (R_eco) to Gross Primary Productivity (GPP). To do so, we developed a simplification of the Soil Carbon dynamics routine proposed in DNDC [1]. The method calculates decomposition as a function of soil moisture, temperature, state of the organic compartments, and relative abundance of microbial pools. Given the pulse dynamics of soil respiration, we introduced modifications in some of the principal constitutive relations involved in phenology and littering sub-routines. We quantified the model structure related uncertainty in NEE, by running our training simulations over 1000 random parameter-sets extracted from parameters distributions expected from literature. 3D-CMCC-PSM predictability was tested on independent time series for 6 Fluxnet sites. The model resulted in daily and monthly estimations highly consistent with the observed time series. It showed lower predictability in Mediterranean ecosystems, suggesting that it may need further improvements in addressing evapotranspiration and water dynamics.

We use the third version of the Canadian Local Climate Model as a diagnostic tool to study the climatology of observed CG lightning activity at Maniwaki (latitude: 46,23°N; Longitude: 75,58°W). We examine the dependence between the hourly lightning activity and the related atmospheric variables during the warm season of sixteen years (between 1984 and 2004). The goal of this research is: a) to evaluate the atmospheric static state evolution and its moisture contents for conditions having generated lightning occurrence, b) to develop a CG lightning parameterization, and c) to verify this CG lightning parameterization on other Canadian areas. The freezing level altitude and the precipitable water content are used to estimate the static air instability and its moisture content respectively. These two parameters are served to develop the CG lightning parameterization. A comparison between the observations and simulations CG lightning occurrence and frequency at Maniwaki showed a mean absolute error rate of 27% and 55% respectively. We apply this parameterization at four Canadian regions, distributed from west to east. The simulated CG lightning results are comparable to observed CG lightning at Maniwaki and tested regions. The application of the CG lightning parameterization to the daily data enabled us to find the monthly results. This application represents a preliminary stage for validation this parameterization in regional numerical models in Canada during the historic period.

This research presents a comprehensive framework for efficiently generating forest fire datasets from Google Earth Engine data sources. The primary contribution of this work lies in providing a methodology to swiftly extract forest fire factors without the need for permissions or access to private datasets, rendering the dataset openly accessible and shared without barriers. Furthermore, given that the remote sensing data used is a global dataset, it can be applied in any region without restrictions. In this study, Peninsular Malaysia is chosen as a case study to demonstrate the framework's effectiveness. The generated dataset includes essential variables including the climate and environment, landcover, topography, and anthropogenic factors facilitating the analysis of fire occurrences. The methodology empowers data scientists, enabling them to leverage their analytical skills on the extracted dataset without requiring specialized remote sensing knowledge. Additionally, this study also showcases the adoption of large language models, specifically GPT-4 with the Noteable plugin, as a tool for conducting preliminary analyses on the generated dataset. Sample analyses reveal that several key features, including the KBDI, LST, PDSI, climate water deficit, and precipitation, significantly impact forest fire occurrences in Peninsular Malaysia. Despite the successful application of the GPT-4 with Noteable plugin, certain limitations and challenges are identified, highlighting the necessity for further validation of the tool's applicability and limitations. This study encourages future research to (1) adopt the proposed framework in other regions, (2) explore more detailed analyses encompassing all variables, and (3) leverage machine learning for advanced forecasting.

Estimating Forest growing stock volume (GSV) is crucial for forest growth and resource management, as it reflects forest productivity. National measurements are laborious and costly, however integrating satellite data such as optical, Synthetic Aperture Radar (SAR), and Airborne Laser Scanning (ALS) with National Forest Inventory (NFI) data and machine learning (ML) methods has transformed forest management. In this study, Random Forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) were used to predict GSV using Estonian NFI data, Sentinel-2 imagery, and ALS point cloud data. Four variable combinations were tested: CO1 (vegetation indices and LiDAR), CO2 (vegetation indices and individual band reflectance), CO3 (LiDAR and individual band reflectance), and CO4 (a combination of vegetation indices, individual band reflectance, and LiDAR). Across Estonia's geographical regions, RF consistently delivered the best performance. In the northwest (NW), RF achieved an R² of 0.63 and an RMSE of 125.39 m³/plot. In the southwest (SW), it achieved an R² of 0.73 and an RMSE of 128.86 m³/plot. In the northeast (NE), RF achieved an R² of 0.64 and an RMSE of 133.77 m³/plot, and an R² of 0.70 and an RMSE of 120.72 m³/plot was achieved in the southeast (SE). These results underscore RF's precision in predicting GSV across diverse environments, though refining variable selection and improving tree species data could further enhance accuracy.

Having in view the sustainable management of forests, the intensity of silvotechnical interventions is analyzed and documented for young mixed beech stands regenerated naturally by taking into account the allometric relationships between some representative dendrometric elements, respectively, between the height of the trees and the corresponding diameter of their crowns. For this purpose, a functional dependence is established between the height and diameter of the tree crown from young beech stands within which silvotechnical interventions were or were not applied. A mathematical model based on cubic spline regression was developed, also taking into account the determination of the average diameter of the crown for each stand. This average diameter can be used to determine the optimal number of trees per surface unit (ha) at a given time. The research was carried out in three young beech stands, through statistical-mathematical inventories, on sample plots of 300 square meters with a tolerance of 10% and a coverage probability of 90%. The optimal diameter of the crown was obtained by applying the spline regression model, and the most appropriate functional dependence was established, resulting in a linear regression law with a positive slope.

Forest above-ground carbon stock (AGCS) is one of the primary ecological evaluation indicators, so it is crucial to estimate AGCS accurately. In this research, we added the climatic and topographic factors to the estimation process by a remote sensing approach to explore their impacts and to achieve more precise estimations. We model and predict AGCS by Random Forest (RF) based on sixty field sample plots of Pinus densata pure forests in southwest of China and the factors extracted from Landsat 8 OLI images (Source I), Sentinel-2A images (Source II), combined Landsat 8 OLI and Sentinel-2A images (Source III). We added the topographic and climatic factors to establish AGCS estimation model and compare the results. The topographic factors contain elevation, slope and aspect. Climatic factors contain mean annual temperature, annual precipitation, annual potential evapotranspiration and monthly mean potential evapotranspiration. It was found that the model based on Source III was better than Source I and Source II. Among the models without adding factors, the model based on Source III worked the best, with an R2 of 0.87, an RMSE of 10.81 t/ha, an rRMSE of 23.19%, and a P of 79.71%. Among the models that added topographic factors, the model based on Source III worked best after adding elevation, with an R2 of 0.89, an RMSE of 10.01 t/ha, an rRMSE of 21.47%, and a P of 82.17%. Among the models that added climatic factors, the model that was added the annual precipitation factor had the best modeling result, with an R2 of 0.90, an RMSE of 9.53 t/ha, an rRMSE of 20.59%, and a P of 83.00%. The prediction result exhibited that the AGCS of the Pinus densata forest in 2021 was 9,737,487.52 t. The combination of Landsat 8 OLI and sentinel-2A could improve the prediction accuracy of AGCS. The addition of annual precipitation can effectively improve the accuracy of AGCS estimation. Higher resolution of climate data is needed to enhance the modeling in the future work.

The conversion of LULC classes into other types is occurring at a faster rate globally including United States. Many studies have examined the drivers and causes of LULC changes, particularly, in northeast Georgia and Atlanta in the United States, while the case of southeast Georgia remains unstudied. Thus, this study filled the gap by quantifying and predicting the impact of LULC change on forestlands and how these LULC changes have affected forest health. The study used Landsat images, including 2005 and 2023 together with the random forest algorithm to perform LULC classification on the Google Earth Engine. Also, the study predicted how LULC will impact forest cover by 2050. The results revealed that forest hectares have generally changed approximately from 65% to 62% between 2005 and 2023, and this is projected to likely further decline to about 53% by 2050. This change in forest acreage has resulted decline in the health of the forest, that is the NDVI values changed from 0.992 to 0.866 between 2005 and 2023. The study concludes that the forest cover in southeast Georgia has changed to urban features over the years. Agriculture land is projected to gain most of the forest cover by 2050.

Forest quality has a significant impact on carbon emissions of the economic system. This paper, based on an analysis of the Environmental Kuznets Curve (EKC) of Forest quality and carbon emission of economic systems, explores effective carbon emission reduction paths from the perspective of symbiosis between Forest quality and economic growth system. This paper carries out empirical analysis based on the provincial-level regional data of China and EKC panel data analysis for several major geographic regions in China. The correlation statistical test shows that the model considering Forest quality is more consistent with the test requirements. It is found that the overall EKC curve of China as a whole shows an inverted U-shape. In light of geographic differences, the EKC curve in the northwest also shows an inverted U-shape; it shows a U-shaped curve in North, Northeast, and East China. Meanwhile, in South Central and Southwest China, there is an approximately linear increasing curve. The data simulation of the symbiotic system of Forest quality and economic growth suggests that simultaneously increasing the proportion of forestry output value and the systematic carbon inhibition coefficient is the most effective pathway for carbon emission reduction. Choosing an appropriate carbon reduction pathway can contribute to the sustainable development of Forest quality and economic growth. The main research highlight of this paper is the application of the symbiotic system model to the EKC analysis of carbon emissions from the economic system with Forest quality.

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

We investigated the cub’s survival in a wild Indian Leopard (Panthera pardus fusca) population in the Jhalana Forest Reserve, India. The research focuses on the survival analysis of leopard cubs during their first two years of life and determining the critical period of the reproductive cycle that influences survival. Survival functions were estimated using the Kaplan-Meier method using data collected with trail cameras over four years from 2018 to 2021. We found that the mean survival probability of cubs during the 2-year period they depend on their mother was 0.618, the first year – 0.739, and higher during the second year of life (0.831). The results also indicate that the first 12 months of a leopard cub's life are crucial for survival. These findings allow for understanding critical periods in the life history of individuals and are essential for effective conservation strategies in fragmented habitats.

Credit business is a vital part of the bank's core business, which has an extremely important impact on the bank's income and development. In the operation of credit business, credit risk assessment is particularly crucial, and accurate risk assessment can minimize risks while maximizing the bank's returns. We propose a method to optimize credit risk assessment using machine learning techniques. In this work, we employ a random forest machine learning model to process and analyze large amounts of loan application data. By using correlation analysis, information enrichment, etc., the characteristics that have the most impact on credit risk assessment are screened. Subsequently, the model was constructed using a random forest algorithm. Random forests improve the generalization ability and accuracy of the model by building multiple decision trees and introducing randomness between these trees. In the experimental analysis part, we compare the performance of various models on the German credit dataset, and the results show that the deep learning model outperforms the traditional machine learning model in most indicators, verifying the effectiveness of our method.

The concentrations and ratios of plant C, N, and P serve as important indicators of ecological processes. However, how plant and soil C:N:P relationships and ratios change with forest stand types remain unclear. Here, we analyzed the ecological stoichiometric characteristics by measuring leaf and soil organic C, total N and P contents in four stand types in Liaocheng, including Populus tomentosa pure forest, Populus tomentosa-Robinia pseudoacacia mixture forests, Platanus orientalis pure forest, and Salix matsudana pure forests. We find that: (1) The N and P leaf contents varied significantly across the four forest stands, with Populus tomentosa-Robinia pseudoacacia mixture forests having higher P levels. Platanus orientalis pure forests had lower C and N but higher P levels compared to others. (2) Uncoupled cycling of P in leaf-soil systems due to environmental influences, but C and N elements showed coupled cycles in some forest stands. (3) All forest stand types were limited by N and P elements. Overall, environmental factors, in addition to species variations, influence the C, N, P, and C:N:P ratios in leaves and soils of different forest stand types. Enhancing conservation and efficient use of N and P elements is crucial for sustainable plantation forest management to promote optimal growth in the region.

This paper explores the utilization of ensemble models and learning analytics techniques to predict student academic performance. With the advent of educational big data, institutions are increasingly leveraging advanced analytics to gain insights into student learning patterns and optimize educational outcomes. Ensemble models, which combine the predictive power of multiple algorithms, offer a robust approach to enhance prediction accuracy. The performance of the ensemble models was analyzed and compared using the Open University Learning Analytics Dataset, which consists of sources such as demographic information, historical performance data, and engagement metrics for 23,344 students. The evaluation of various ensemble models across different classification scenarios revealed that the proposed stacking model consistently emerges as the best-performing model, excelling in both multi-class and binary classification tasks.

As the largest carbon pool on Earth, forest ecosystems are essential to maintaining carbon sink balance. However, accurately estimating the carbon sequestration and carbon storage of forest resources remains an urgent issue to address. Plot investigation, model estimation, and machine learning are examples of current approaches. Nevertheless, because of variables such as regional characteristics and plot size, large-scale and extensive region estimates are comparatively scarce. This study, which focuses on Tianzhu County, aims to comprehensively analyze and estimate the Net Primary Productivity (NPP), carbon storage, and carbon density of the forest ecosystem in this area by integrating data from forest resource inventory and the CASA model. The main conclusions are as follows: (1) The main vegetation types in Tianzhu County include coniferous forests, broad-leaved forests, mixed forests, and shrub forests; (2) Accordin g to the CASA model calculations, the annual cumulative NPP in Tianzhu County in 2020 ranges from a maximum of 249.63 gC/m² to a minimum of 3.40 gC/m², with the forest NPP amounting to 134,674.65 tons of carbon. Based on MODIS observation data, the forest’s NPP is 171,728.32 tons of carbon, with a maximum of 325.36 gC/m² and a minimum of 0.02 gC/m²; (3) At the pixel scale, the carbon storage of forests in Tianzhu County is 361,700 tons. Specifically, 46,500 tons of carbon are stored in coniferous forests, 1,100 tons in broad-leaved forests, 500 tons in mixed forests, and 313,600 tons in shrub forests.

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

Despite the availability of COVID-19 vaccines, the global pandemic remains a significant health challenge. Timely detection of the virus is crucial for effective containment efforts, prompting the exploration of machine learning (ML) models for COVID-19 detection. highlights the ongoing significance of COVID-19 as a global health crisis despite the availability of vaccines. To address the need for timely virus detection, the study explores the efficacy of machine learning (ML) models, including DNN, Voting, Bagging, SVC_rbf, SVC_linear, SVC_polynomial, and SVC_sigmoid, in predicting COVID-19 infection probability. With a dataset comprising 4000 samples split into 3200 for training and 800 for testing, the analysis reveals that DNN and Voting models demonstrate the highest performance, achieving an impressive accuracy of 89%. These results underscore the potential of ML techniques, particularly DNN and ensemble methods like Voting, in facilitating early COVID-19 detection and contributing to effective pandemic management. The study emphasizes the importance of continued research to further refine and optimize ML-based COVID-19 detection systems.

This study was to identify clinical cancer biomarkers for recurrent gastric cancer survivors using artificial intel-ligence. From a hospital-based cancer registry database in Taiwan, the datasets of the incidence of recurrence and clinical risk features were included in 2476 gastric cancer survivors. We benchmarked Random forest with MLP, C4.5, AdaBoost, and Bagging algorithms on metrics and leveraged synthetic minority oversampling technique (SMOTE) for imbalanced dataset issues, cost-sensitive learning for risk assessment, and SHapley Additive ex-Planations (SHAP) for feature importance analysis in this study. Our proposed Random forest outperformed the other models with an accuracy of 87.9%, a recall rate of 90.5%, an accuracy rate of 86% and F1 of 88.2% on re-current category by a 10-fold cross-validation in a balanced dataset. We identified clinical features of recurrent gastric cancer, which are the top five features, stage, number of regional lymph node involvement, Helicobacter pylori, BMI(body mass index), and gender, which significantly affect the prediction model's output, are worth paying attention to in the following causal effect analysis. Using an artificial intelligence model, the risk factors for recurrent gastric cancer could be identified and cost-effectively ranked according to their feature importance. In addition, they should be crucial clinical features to provide physicians with the knowledge to screen high-risk patients in gastric cancer survivors as well.

Garlic, as an important economic crop in China, still has room for improvement in terms of identification using remote sensing technology, Among them, high-precision classification of garlic has become an important subject. The Erhai Lake is an important freshwater lake in China. Under the influence of technology and policies, significant changes have occurred in the cultivation of garlic crops. this study constructed multidimensional features for crop classification suitable for Google Earth Engine, and Propose a method for identifying garlic crops using sample and feature datasets under limited conditions. The results indicate that: 1) In the land-use classification of the Erhai Lake Basin, the importance ranking of characteristic bands, from high to low, is as follows: spectral features, vegetation features, texture features, and terrain features. 2) The Random Forest method based on feature selection demonstrates high classification accuracy in land-use classification within the Erhai Lake Basin in Yunnan Province. The overall classification accuracy reaches 95.79%, with a Kappa coefficient of 0.9481. 3) The expansion direction of garlic cultivation in the Erhai Lake Basin initially strengthened and then weakened from 1999 to 2023. The vertical development of garlic cultivation reached saturation, showing a slow trend towards horizontal expansion between 2005 and 2018. The planting distribution in various townships in the Erhai Lake Basin gradually shifted from a relatively uniform distribution to an upstream development in the basin. This study utilizes the Google Earth Engine (GEE) cloud computing platform and machine learning algorithms to compensate for the lack of statistical data on garlic cultivation in the Erhai Lake Basin. Simultaneously, it accurately, rapidly, and efficiently extracts planting information, demonstrating significant potential for practical applications.

Land surface temperature (LST) is a critical parameter for land surface and atmospheric interactions. However, the applicability of current land surface temperature estimates for field-level hydrological, agricultural, and ecological operations is still challenging due to their coarse spatiotemporal resolution. In the current article, we have downscaled 100 m LST to 10 m by using high-resolution Sentinel-1,2 optical-microwave data and three different models- 1) Thermal Sharpening (TsHARP); 2) Thin Plate Spline (TPS); and 3) Random Forest (RF). The extensive analysis was performed at agricultural farms in the semi-arid (IARI) region of India during the winter and summer seasons of 2020-21 and 2021-22, arid (CAZRI) and per-humid (UBKV) region (2021-2022). The calibration accuracy of the RF model was shown to better agreement with the coefficient of determination (R2) of 0.982, root means square error (RMSE) 0.181 and normalized root means square error (RMSE) 0.061 with their lower values of standard errors over three diverse agro-climatic zones. The findings demonstrate that the validation accuracy of models' varied according to the agroclimatic zones, although RF and TPS consistently outperformed as compared to the TsHARP models.

Despite being considered as natural components of many ecosystems, forest fires pose significant threats to the environment and human health. In order to ensure public safety and effective fire suppression planning, it is necessary to develop reliable prediction models to mitigate forest fire danger. These models should account for specific environmental conditions. The advent of big data in recent years has opened new avenues for improving forest fire predictions. Machine learning techniques, surpassing traditional forecasting methods, have shown significant promise in this area. By applying the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology to a real-world dataset, this paper explores the application of machine learning approaches to understand forest fire patterns and predict fire danger. We consider six distinct time stages and incorporate feature selection to refine our predictions. It is important to note that forest fire behavior models are not universally effective due to geographical variations in data. Nevertheless, advanced decision-making techniques are vital in forest fire management. Our research presents a systematic exploration of the topic, comparing various machine learning models, thereby providing a comprehensive baseline for future investigations in this crucial environmental arena.

Gelephu, located in the Himalayan region, has experienced one of the strongest development activities due to the suitable topography and geographic location, which has led to rapid urbanization. The main objective of the study is to perform land use land cover (LULC) mapping for Gelephu for 2016 and 2023 by a Random Forest (RF) classifier, using the Semi-automatic Classification Plugin (SCP) in QGIS and identify LULC changes. Furthermore, the study assessed the vegetation change dynamics within the study area by analysing the Normalized Difference Vegetation Index (NDVI) for 2016 and 2023. Additionally, the study characterized the resulting LULC change for Gelephu Thromde, a sub-administrative municipal entity, as a result of the notable intensity of the infrastructure development activities. The current study used a framework to collect Sentiniel-2 satellite data, which was then used for pre- and post-processing to create LULC and NDVI maps. The classification model achieved high accuracy, with an area under the curve (AUC) of up to 0.89. The corresponding LULC and NDVI statistics were analysed to determine the current status of the LULC and vegetation indices, respectively. The LULC change analysis reveals urban growth of 5.65% and 15.05% for Gelephu and Gelephu Thromde, respectively. The NDVI assessment shows significant deterioration in vegetation health with a 75.11% loss of healthy vegetation in Gelephu between 2016 and 2023. This research provides the first version of LULC and NDVI maps of Gelephu. The analysis results indicate possible future implications on sustainable development management in Gelephu Bhutan.

The accurate estimation of biomass carbon in forests is of paramount importance for effective forest management and mitigating climate change. This study presents a novel approach to produce a high-resolution map of biomass carbon over forests in Malaysia using the Aboveground Carbon Density Indicator (ACDI) and a comprehensive collection of 12 years of inventory data, i.e., from 2012 to 2023. The ACDI was derived based on several vegetation indices (VIs) that were produced from the original Landsat images to indicate the level of aboveground biomass carbon (AGC) stock in the forested areas. The VIs includes Normalised Difference Vegetation Index (NDVI), Normalised Burn Ratio (NBR), Shadow Index (SI), Soil-Adjusted Vegetation Index (SAVI), Iron Oxide Index (IO), Modified Normalised Difference Water Index (NDWI), and Enhanced Vegetation Index (EVI). The ACDI was then integrated with ground-based measurements, and serves as a robust indicator for estimating AGC. This calculation was conducted on Google Earth Engine (GEE) platform to match the date of field observation with the satellite imagery datasets. The production of seamless mosaic of the latest date of Landsat imagery and the forest type classification were also performed on GEE. The forested areas were classified into three major types, which are dry inland forest, mangrove forest, and peat swamp forest. Results indicated significant spatial variations in AGC across Malaysia's forests. The derived AGC prediction models based on the ACDI varied among the forest types. Based on the estimates, a 30-metre resolution, wall-to-wall map of AGC across the entire forested region of Malaysia has been created. The ACDI was calibrated and validated using a separate validation plots dataset to ensure the accuracy of the AGC estimates. The total AGC in all types of forests in Malaysia was estimated at 3.0 billion Mg C with an attainable accuracy of about 80%. These estimates were also divided into categories and reported to the AGC at the state level. This high-resolution map provides essential information for various stakeholders, with critical implications for carbon sequestration efforts, conservation priorities, and sustainable forest management. The presented methodology not only showcases the value of combining advanced remote sensing techniques with long-term inventory data but also underscores the potential for similar approaches in other tropical forest regions globally. Ultimately, this study contributes to the understanding of carbon dynamics in Malaysian forests and promotes effective strategies for mitigating climate change through better-informed forest conservation and management practices.

Random Forest (RF) is a widely used data prediction and variable selection technique. However, the variable selection aspect of RF can become unreliable when there are more irrelevant variables than relevant ones. In response, we introduced the Bayesian Random Forest (BRF) method specifically designed for high-dimensional datasets with a sparse covariate structure. Our research demonstrates that BRF possesses the oracle property, which means it achieves strong selection consistency without compromising efficiency or bias.

This study utilizes the Random Forest technique to investigate risk management practices and concerns in Islamic banks using survey data from 2016 to 2021. Findings reveal that larger banks provide more consistent survey responses, driven by their confidence and larger survey budgets. Moreover, a positive link is established between a country's development, characterized by high GDPs and low inflation and interest rates, and the precision of Islamic banks' survey responses. Analyzing risk-related concerns, the study notes a significant reduction in credit portfolio risk, attributed to improved risk management practices, global economic growth, stricter regulations, and diversified asset portfolios. Concerns related to terrorism financing and cybersecurity risks have also decreased due to better enforcement of anti-money laundering regulations and investments in cybersecurity infrastructure and education. This research enhances our understanding of risk management in Islamic banks, highlighting the impact of bank size and country development. Additionally, it emphasizes the need for ongoing analysis beyond 2021 to account for potential COVID-19 effects and evolving risk management and regulatory practices in Islamic banking.

Sustainable Forest Management (SFM) can fully use forest resources and improve the economic, environmental and social sustainability of forest areas. Forestry enterprises play a crucial role in the implementation of SFM. To better play the role of forestry enterprises in implementing SFM, it is necessary to establish a comprehensive and reasonable performance evaluation model for SFM in forestry enterprises. However, the previous literature pays little attention to this research question. Taking the Triple Bottom Line (TBL) as a theoretical framework and the Montreal Process Criteria and Indicators (MP C&I) as a basis, this paper constructs an indicator system to evaluate the performance of SFM of forest enterprises from economic, social and environmental aspects. This paper applies the integrated MCDM method, i.e. the BWM method and the VIKOR method, to construct the methodological system for SFM performance evaluation of forestry enterprises. The effectiveness of this SFM performance evaluation model is then demonstrated through its application to a case study of forestry enterprises in China. Through the application of the model, this paper evaluates the enterprise's SFM performance over the five-year period 2017-2021 and proposes appropriate policy recommendations and improvements.

Introduction: In recent decades, health literacy, in connection with a broad range of public 1 health terms, has become a burgeoning field. This study aims to explore trends and biases in this 2 area through a bibliometric analysis. Methods: A Random Forest Model was utilized to identify 3 keywords and other metadata that predict annual citations in the field. In order to supplement 4 this machine learning analysis, we have also implemented a bibliometric review of the corpus. 5 Results: Findings indicate a high positive coefficient for the keyword ’Covid-19’ and ’Male’, whereas a 6 negative coefficient was observed for ’Female’, suggesting potential biases. Evolving themes such as 7 Covid-19, Mental Health, and Social Media were discovered. A significant shift was noted in the main 8 publishing journals, while the major contributing authors remained the same. Discussion: The results 9 hint at the influence of the Covid-19 pandemic and potential gender biases on citation likelihood, as 10 well as changing publication strategies despite the fact that the main researchers remain as the ones 11 that have been studying health literacy since its creation.

This study examined ways to prevent failures in the front-end of forklifts by addressing the center of gravity of heavy objects carried by forklifts, predicting the remaining useful lifetime (RUL), and the fault diagnosis based on alarm rules. In the research process, acceleration signals were acquired from the outer beam of the front-end of the forklift. A one-second window was applied to extract the time-domain statistical features, which were then set as variables. An exponentially weighted moving average was used to smooth the noise in the feature data set. The AWGN and LSTM autoencoders were used for data augmentation. Based on them, random forest and lightGBM models were used to develop classification models for the weight center of heavy objects carried by a forklift. In addition, contextual diagnosis performed by applying exponentially weighted moving averages to the classification probabilities of the machine learning models showed that random forest achieved an accuracy of 0.9563 and lightGBM achieved an accuracy of 0.9566. In addition, the acceleration data were collected through experiments to predict forklift failure and RUL because of the repeated forklift use when the center of heavy objects carried by the forklift was skewed to the right. The time-domain statistical features of the acceleration signals were extracted and set as variables by applying a 20-second window. Subsequently, logistic regression and random forest models were used to classify the failure stages of the forklifts. The f1-score (macro) obtained were 0.9790 and 0.9220 for logistic regression and random forest, respectively. In addition, the random forest probabilities for each stage were combined and averaged to generate a degradation curve and derive the failure threshold. The coefficient of the exponential function was calculated using the least squares method on the degradation curve, and the RUL prediction model was developed to predict the failure point. In addition, the SHAP algorithm was used to identify the significant features in classifying the stage. The alarm rule-based fault diagnosis was performed using the threshold of the normal stage distribution of the significant features.

Quantitative evaluation of the musical timbre and its variations is important for the analysis of audio recordings and computer-aided music composition. Using the FFT acoustic descriptors and their representation in an abstract timbral space, variations of a sample of monophonic sounds of chordophones (violin, cello) and aerophones (trumpet, transverse flute, and clarinet) sounds are analyzed. It is concluded that the FFT acoustic descriptors allow us to distinguish the timbral variations of the musical dynamics, including crescendo and vibrato. Furthermore, using the Random Forest algorithm, it is shown that the FFT-Acoustic provides a statistically significant classification to distinguish musical instruments, family of instruments, and dynamics. We observed a better behavior for the FFT-Acoustic descriptors when classifying pitch compared to some timbral features of Librosa.

Forest ecosystems provide diverse services and values that contribute to human well-being. Although high proportion of species is still undiscovered, tropical forests alone are thought to host more than 50% of the world’s biodiversity. Beyond supporting via direct use of products like timber, fiber and biomass energy, they play an important role in providing a wide range of ecosystem services such as regulating water flow and quality, water purification, improving infiltration, fresh water, erosion control, carbon sequestration and sedimentation control. They are one of the important parts of terrestrial and the largest carbon pool, occupying an integral position in the global carbon cycle. However, these days, deterioration of nature and forest biodiversity is a severe danger to the global environment. This will be accompanied by increased strains on food supply, causing increased pressure on already delicate ecological systems. Thus, better forest management strategies are necessary for managing forests sustainably. Nevertheless, little is known regarding the existing forest management approaches and their associated benefits and challenges. Multidisciplinary approaches are needed to achieve sustainable management of forests. These can be accomplished if suitable forest management innovations are put in place. Various technologies can also be adopted through applying different forest assessment tools like remote sensing using light detection and ranging technology (LiDAR) in forest management. Harnessing such technologies will definitely result in providing increased socio-economy as well as improved environmental sustainability. However, the speed of transformation depends much on level of commitment of stakeholders including policy makers. As a result, this review is intended to explore existing forest management innovations which are suitable both ecologically as well as socio-economically. This shows that while there is a lot to be improved, there are already developed forest management innovations that are already in use including PFM and MFM, which helps to achieve SFM.

Soil texture is a key property influencing most soil physical, chemical, and biological processes and its catchment-scale spatial variation may yields insights for soil management. Texture data are generally available only at a few locations, since sampling and laboratory analyses are time consuming. Therefore, it is essential to predict soil size particles texture variability using appropriate methods. Moreover, soil texture distribution across a catchment is influenced by erosion and sedimentation processes controlled by hillslope morphology, which can be quantified through some topographic attributes. The study was aimed to evaluate the ability of a multivariate approach based on non-stationary geostatistics to merge remotely sensed high-resolution LiDAR-derived topographic attributes with Vis-NIR diffuse reflectance spectroscopy and laboratory analysis to produce high-resolution maps of soil sand content and estimation uncertainty in a forested catchment in southern Italy. Moreover, the proposed approach was compared with the commonly used univariate approach of ordinary kriging. Soil samples were collected at 135 locations within a 139 ha-forest catchment with granitic parent material and subordinately alluvial deposits, where soils classified as Typic Xerumbrepts and Ultic Haploxeralf crop out. A number of linear trend models coupled with different auxiliary variables were compared and the best one resulted the model using clay content as auxiliary variable. The improvement of estimation from using only LiDAR data (elevation) compared to the univariate (no trend) model was rather marginal.

Amidst nature's enchanting embrace, forests stand as revered guardians, safeguarding biodiversity and nurturing rural livelihoods. In this journey, a qualitative study takes flight, exploring the cherished perspectives of the community within Iligan City's rustic expanse in Iligan City, Philippines. Its purpose? To unveil the intricate dance between forest conservation efforts and local livelihood strategies, weaving a tapestry of understanding. Through heartfelt conversations and keen observations, a diverse ensemble of 30 participants shares their wisdom, as thematic analysis reveals its breathtaking hues. In this symphony of voices, the community's resounding admiration for forest conservation emerges, painting a vivid portrait of its ecological significance and cultural splendor. As the canvas unfolds, the participants unfurl the whispered secrets of forest benefits—the gentle preservation of water resources and the enchanting pathways to ecotourism. Yet, amidst this beauty, they tenderly acknowledge the delicate trade-offs, where access to resources finds limitations. And so, the forest emerges as a steadfast companion in their livelihood odyssey, bestowing subsistence resources, opportunities for fruitful endeavors, and a profound sense of cultural heritage. These heartfelt discoveries beckon us to embrace the wisdom of the community, intertwining local perspectives into the fabric of forest conservation strategies, and championing participatory approaches that resonate with shared hopes and dreams. This study bestows upon us precious insights, illuminating the path towards sustainable forest management—a harmonious union where conservation goals and the vibrant tapestry of local livelihood needs dance hand in hand. Overall, locals must heed the profound symphony woven by forests and livelihood, as policymakers and practitioners craft a future where nature's melodies echo in the hearts of all who call the forest their home.

The urban environment induces stress on trees and the impact can be identified by observing the condition of the crown. The aim of this study is to correlate the variables crown density (Cdn), crown transparency (Ctr) and dieback (Cdie) with the following vegetation indices: normalized difference vegetation index (NDVI), enhanced vegetation index (EVI2), blue normalized difference vegetation index (BNDVI), green normalized difference vegetation index (GNDVI), green-red vegetation Index (GRVI) and red-green-blue vegetation index (RGBVI) of the tree crown located in urban green areas, as well as chlorophyll fluorescence (Fv/Fm) as an indirect indicator of tree health condition. A total of 549 trees were evaluated, represented in 24 families, 36 genera and 53 species; the variables had average values of 67.96 % in Cdn, 35.19 % in Ctr and 1 % in Cdie. Correlations were found between Fv/Fm, NDVI and BNDVI. NDVI and BNDVI correlated with variables such as Cdn and Ctr, mainly in species such as Ligustrum lucidum, Jacaranda mimosifolia and Fraxinus uhdei. Therefore, it is possible to evaluate tree health condition of trees in urban green environments through the identification of unfavorable conditions at the crown level by using vegetation indices for some of the species studied.

Since the COVID-19 pandemic, urban forest mountains have become important restorative environmental spaces, and demand-customized management based on users’ experiences is needed. We collected 21,557 data points from blogs from January 2020 to December 2021. For data analysis, keyword frequency, term frequency-inverse document frequency, and sentiment analyses were conducted using TEXTOM 4.0, and a semantic linkage network was established and analyzed using Gephi 0.92. In the analyses, the restorative environment components of “being away” “fascination,” “extent,” and “compatibility” were derived from users’ experiences. Fascination, which stems from natural objects such as rocks, valleys, and trails, was derived the most frequently, and being away and compatibility, representing leisure activities such as climbing and walking, formed the largest cluster in cluster analysis. Sentiment analysis revealed a high positive word rate of 91.6%, with favorable feelings accounting for 87.5%, whereas the proportions of joy and interest (12.5%) were relatively low. This study showed that leisure activities related to nature objects had a positive impact. However, joy and interest, which correspond to vitality, were relatively lacking in the restorative experience. To improve restorative experience quality, diversification of leisure activities should be promoted and customized management plans corresponding to restorative environment components developed.

Background: Public engagement is needed to make sure urban forestry management efforts align with the values of the public being served. Noting this, we determined current and desired urban forest access of Florida (United States) residents using the criteria from the 3-30-300 rule (i.e., 3 trees visible from home, 30% canopy in neighborhood, and a green space within 300 meters of home). Methods: A survey of 1,716 Florida residents was conducted to assess canopy coverage and green space access. Respondents were then asked if this level of urban forest access was sufficient for their needs. We also asked their perceptions of the benefits and drawbacks of urban trees and whether they had any negative interactions with trees in the past. Results: We found that 37.3% of Florida residents met all three criteria of the 3-30-300 rule. Despite this, half the respondents would prefer more trees in their neighborhoods. When asked to name the top benefits provided by trees, the most common responses were shade, beauty, and attracting wildlife. The most common drawbacks to urban trees included risk to property, leaves/debris, and fears regarding storms and hurricanes. Conclusions: Florida residents largely value their urban forest and would like to see it maintained or enhanced. Improving access to greenspaces for recreation is the most pressing concern for urban forest managers in Florida looking to meet the requirements of the 3-30-300 rule. Results from this study can inform and test urban forest management at national and global scales.

The stator winding insulation system is the most critical and weak part of the EMU's (electric multiple unit) traction motor. The effective diagnosis for stator ITSC (inter-turn short-circuit) faults can prevent the fault from expanding into phase-to-phase or ground short-circuits. The TCU(traction control unit) controls the traction inverter to output SPWM (sine pulse width modulation) excitation voltage when the traction motor is stationary. Three ITSC fault diagnostic conditions are based on different IGBTs control logic. The Goertzel algorithm is used to calculate the fundamental current amplitude difference Δi and phase angle difference Δθ of equivalent parallel windings under the three diagnostic conditions. The six parameters under the three diagnostic conditions are used as features to establish an ITSC fault diagnostic model based on random forest. The proposed method was validated using a simulation experimental platform for ITSC fault diagnosis of EMU traction motors. The experimental results indicate that the current amplitude features Δi and phase angle features Δθ change obviously with the increase of ITSC fault extent if the ITSC fault occurs at the equivalent parallel windings. The accuracy of the ITSC fault diagnosis model based on the random forest for ITSC fault detection and location both in train and test samples are 100%.

Forest fires are one of the world's deadliest natural disasters. Early detection of forest fires can help minimize the damage to ecosystems and forest life. In this paper, we propose an improved fire detection method YOLOv5-IFFDM for YOLOv5. Firstly, the fire and smoke detection accuracy and the network perception accuracy of small targets are improved by adding attention mechanism in the backbone network. Secondly, the loss function is improved and the SoftPool pyramid pooling structure is used to improve the regression accuracy and detection effect of the model and the robustness of the model. In addition, random Mosaic augmentation technique is used to enhance the data to increase the generalization ability of the model, and re-clustering of flame and smoke detection a priori frames are used to improve the accuracy and speed. Finally, the parameters of the convolutional and normalization layers of the trained model are homogeneously merged to further reduce the model responsibility to improve the detection speed. Experimental results on homemade forest fire and smoke datasets show that this algorithm has high detection accuracy and fast detection speed, with average accuracy of fire up to 90.5% and smoke up to 84.3%, and detection speed up to 75 FPS (frames per second transmission), which can meet the requirements of real-time and efficient fire detection.

Insect outbreaks are major drivers of natural disturbances in forest ecosystems. Outbreaks can have both direct and indirect effects on the composition of soil arthropod communities, through canopy opening, nutrient addition and predator-prey interactions. In this study, we aim to understand the effects of forest tent caterpillar (Malacosoma disstria; FTC) outbreaks on ant communities in both temperate and boreal forests in Canada. Using pitfall traps and Berlese funnels, we compared the ant communities as well as the surrounding arthropod communities between control and outbreak sites in boreal andboreal and temperate forests (in Québec, Canada). Using the Sørensen dissimilarity index, we determined the alpha and beta diversity of the ant community. Other arthropods collected in the traps were counted to evaluate the richness and abundance of potential prey for the ants and other potential predators of the FTC. We used an indicator species analysis to examine the species associated with sites defoliated by the outbreak. In the boreal forest, we found that FTC outbreaks caused decreases in species richness and increases in the evenness of ant communities in defoliated sites. In the boreal forest sites, species composition varied significantly between control and outbreak sites. This pattern was driven by the presence of other predators. We also saw no changes in beta diversity in the boreal forest but did see a significant decrease in the temperate forest between the outbreak sites and the control sites. A similar, but weaker pattern was observed in the temperate forest. Ant species in the boreal forest tended to exhibit a more marked preference for either control or previously defoliated sites than species in the temperate forest. Our study showed that disturbances like insect outbreaks can drive changes in the ant community. While we saw small effects of outbreaks, manipulation experiments using resource addition could help us validate the mechanisms behind these relationships.

The Azores bullfinch (Pyrrhula murina Godman, 1866) is a rare Passeriformes endemic from the eastern part of São Miguel Island. This bird was almost considered extinct in the first half of the 20th century and, due to recent conservation measures, it has experienced a recovery since the beginning of the 2000s. Despite the attention given to this bird, the size of its population is still controversial, and the most recent studies present significant divergences on this behalf. The pur-pose of the present study is to present data from the long-term monitoring of the Azores bullfinch to update the information about the population size and range of this species. In addition, we performed a literature review to highlight the limitations and advantages of the different ap-proaches for monitoring this species. In this study, we conclude that the most likely size of the Azores bullfinch population is 500 to 800 couples, with a slow population growth tendency, and an area of distribution of 130 Km2.

Tree ordinances can be an effective means of preserving urban forests in the face of development pressures. Despite this, they also have the potential to be divisive among the public - especially when applied to privately-owned land. In this study we surveyed 1,716 Florida urban residents to understand how they value regulation and management of the urban forest. Specifically, we asked about: tree protection ordinances, incentive programs to manage or plant trees, justification for tree removal, and development. Most respondents supported tree protections, even when applied to trees on their own property or when they had the potential to limit development activities. Additionally, there was limited support for removing healthy trees for development. Respondents supported the use of funds for urban forestry efforts – particularly at the local or state level.

Browsing of wild ungulates can have profound effects on the structure and composition of forests. In the Swiss National Park, the density of wild ungulates including red deer (Cervus elaphus), ibex (Capra ibex), and chamois (Rupicapra rupicapra) is exceptionally high due to strict protection and the absence of large predators. We examined count data of larch (Larix decidua), cembra pine (Pinus cembra), spruce (Picea abies), upright mountain pine (Pinus mugo subsp. uncinata), and mountain ash (Sorbus aucuparia) of four sampling years between 1991 and 2021 and modelled how different topographic and location factors affected the probability of browsing on saplings of larch, cembra pine, and spruce. Despite the high density of wild ungulates, the numbers of saplings and young trees increased over the past 30 years. The probability of browsing on saplings was highest for larch at a height of 10 – 40 cm and increased with increasing elevation. In our study area, open grasslands are mainly located above the tree line, which might explain the positive correlation between elevation and the probability of browsing. Other factors like exposition and slope, available food resources and disturbance by humans did not have clear effects on the probability of browsing.

In its Nationally Determined Contribution (NDC) to the United Nations Framework Convention on Climate Change, Brazil committed to reducing greenhouse gas emissions and restoring its forests. This study examines the challenges of fulfilling these commitments in Brazilian Amazonia. We carry out a detailed assessment of the current status of land tenure in the region and its relation to deforestation. After dealing with conflicts and overlaps between data from various sources, we produce a new map of public and private land tenure in Amazonia. Combining this map with Brazil's official data on deforestation, we find out how much natural vegetation has been preserved in each public or private area. The result is used to estimate how much deforestation is illegal. We also establish how much deforestation is associated with each land tenure type. Our results show that most deforestation inside rural properties is done by a few landowners, a finding that has important consequences for law enforcement. We then assess the challenges for reforestation in detail. To do so, we consider how much forest needs to be rehabilitated according to Brazil's Forest Code. Our analysis provides a comprehensive appraisal of the potential opportunity costs for forest restoration in the biome, considering farm size and land use. This analysis provides insights into targeted land use policies that can meet Brazil’s forest restoration goals.

Efficient natural resource management prevents and reduces negative impacts, such as environmental damage, misappropriation of resources, and conflicts; several strategies can be leveraged to conserve, protect, and enhance natural resources. Multi-criteria decision analysis (MCDA) is useful in providing solutions to addressing decision-choice problems. In this study, the natural resource under evaluation is the chestnut forest, with the objective of valorising its supply chains. The methodology applied is A'WOT, which allows previously identified factors through a qualitative SWOT matrix, to be ordered through an objective quantification using AHP (Analytic Hierarchy Process), which is a multicriteria decision-support method. The survey was conducted with a group of chestnut resource (n=20) experts. The SWOT matrix identified a total of 20 factors: 6 strengths and 6 weaknesses and 4 factors each for opportunities and threats. The results express a clear stakeholder interest, which identifies the significant role of civil society in directing management choices for the provision and enhancement of ecosystem and vocational services. This study evaluated the adaptability of decision-support tools applied to a real case of forest resource management to identify and order factors useful to enhance the resource and stimulate the supply chains to achieve greater added value. In a general sense, the methodological potential emerged to replicate or improve the research in other geographical regions, whether regional or extra-regional, or even on a larger scale, such as on a national level.

Read-Across Structure-Activity Relationship (RASAR) is an emerging cheminformatic approach that combines the usefulness of a QSAR model and similarity-based Read-Across predictions. In this work, we have generated a simple, interpretable, and transferable quantitative-RASAR (q-RASAR) model which can efficiently predict the cytotoxicity of TiO2-based multi-component nanomaterials. The data set involves 29 TiO2-based nanomaterials which contain specific amounts of noble metal precursors in the form of Ag, Au, Pd, and Pt. The data set was rationally divided into training and test sets and the Read-Across-based predictions for the test set were generated using the tool Read-Across-v4.1 available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home. The hyperparameters were optimized based on the training set data and using this optimized setting, the Read-Across-based predictions for the test set were obtained. The optimized hyperparameters and the similarity approach, which yields the best predictions, were used to calculate the similarity and error-based RASAR descriptors using the tool RASAR-Desc-Calc-v2.0 available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home. These RASAR descriptors were then clubbed with the physicochemical descriptors and were subjected to features selection using the tool Best Subset Selection v2.1 available from https://dtclab.webs.com/software-tools. The final set of selected descriptors was used to develop multiple linear regression based q-RASAR models, which were validated using stringent criteria as per the OECD guidelines. Finally, a random forest model was also developed with the selected descriptors. The final machine learning model can efficiently predict the cytotoxicity of TiO2-based multi-component nanomaterials superseding previously reported models in the prediction quality.

Vegetation indexes help perform precision farming because they provide useful information regarding moisture, nutrient content, and crop health. Primary sources of those indexes are satellites and unmanned aerial vehicles equipped with expensive multispectral sensors. Reducing the price of obtaining such information would increase the availability of precision farming for small farms. Several studies have proposed deep neural network methods to estimate the indexes from RGB color images. However, these methods report relatively large errors for mature plants when highly non-linear relationships of images and vegetation indexes arise. One could apply multilayer random forest-based models (Deep Forests) to solve this problem, but the discriminative power of such models is limited: they cannot catch complex dependencies between image features. In this paper, we propose a method that combines ideas of deep forests, random forests of kernel trees, and global pruning of random forests to tackle the problem. As a result, the method considers the properties of objects with a complex structure: the presence of relationships between groups of features, displacement, and scaling of objects. The experimental results show that the proposed method outperforms neural network-based solutions in several datasets.

Video segmentation is crucial in a variety of practical applications especially in computer visions. Most of recent works in video segmentation are focusing on Deep learning based video segmentation, there are rooms for improvement in respect of the evolutionary algorithms. This paper aims to propose the novel method to video segmentation by using the optimization of segmentation parameters based on ensemble-based random forest and gradient boosting decision tree. The experimental results show Pareto front of segmentation parameters (hue, brightness, luminance, and saturation). Our optimization model yields accuracy: 85% +/-8.85 % (micro average: 85.00 %), average class precision: 84.88%, and average class recall: 85%. We also show the video segmentation results based on our optimization method and compare our results with Kinect-based video segmentation.

Extraordinary high aerosol contamination observed in the atmosphere over Kyiv city, Ukraine, during the March – April 2020 period. The source of contamination was the large grass and forest fires in the northern part of Ukraine and the Kyiv region. The level of PM2.5 load investigated using newly established AirVisual sensors mini-network in five areas of the city. The aerosol data from the Kyiv AERONET sun-photometer site analyzed for that period. Aerosol optical depth, Angstrom exponent, and the aerosol particles properties (particles size distribution, single-scattering albedo, and complex refractive index) were analyzed using AERONET sun-photometer observations. The smoke particles observed at Kyiv site during the fires in general correspond to aerosol with optical properties of biomass burning particles. The variability of the optical properties and chemical composition indicates that the aerosol particles in the smoke plumes over Kyiv were produced by different burning material and phases of vegetation fires at different time. The case of enormous PM2.5 aerosol contamination in Kyiv city reveals the need to accept strong measures for forest fire control and prevention in Kyiv region, especially in the north-west region where radioactive contamination from Chornobyl disaster is still significant.

Forests constitute a key component of the Earth system but the sustainability of the forest reserves in the semi-arid zone is a real concern since its vegetation is very sensitive to the climate fluctuation. The understanding of the mechanisms for the interaction vegetation-climate is poorly studied in the context of African Sahel. In this study, the characteristics of the vegetation response to the fluctuations of precipitation and temperature is determined for the forest reserve of Fina. Rainfall estimates, air temperature and NDVI are used to establish the lag correlations between fluctuations of vegetation and climate variables at both seasonal and interannual bases. Results shows increasing tendency of NDVI started from the 1990s coinciding the recovery of the rainfall from the 1980s drought and the obtained correlation(r=0.66) is statistically significant (pvalue<0.01). The strongest responses of vegetation to rainfall and temperature fluctuations were found after 30 and 15 days, respectively. Moreover, at shorter time lag (e.g. 15 days) more pronounced vegetation responses to both rainfall and temperature were found in agricultural dominated land while at longer time lag (e.g. 30 days) stronger response was observed in Bare dominated land. The vegetation response to the climate fluctuation is modulated by the land use/cover dynamics. Keywords: NDVI, Rainfall, Air temperature, vegetation response, Fina Forest Reserve, Mali.

The disastrous 2017 fire season in Portugal lead to widespread recognition of the need for a paradigm shift in forest and fire management. We focused our study on Alvares, a parish in central Portugal which had 60% of its area burned in 2017, with a large record of historical. We evaluated how different fuel treatment strategies can reduce wildfire hazard in Alvares, through i) a fuel break network with different priorities and ii) random fuel treatments resulting from stand-level management intensification. To assess this, we developed a stochastic fire simulation system (FUNC-SIM) that integrates uncertainties in fuel distribution over the landscape. If the landscape remains unchanged, Alvares will have large burn probabilities in the north, northeast, and center-east areas of the parish that are very often associated with high fire line intensities. The different fuel treatment scenarios decreased burned area between 12.1-31.2%, resulting from 1%-4.6% increases in annual treatment area, and reduced 10%-40% the likelihood of wildfires larger than 5000 ha. On average, simulated burned area decreased 0.22% per each ha treated, and effectiveness decreased with increasing area treated. Overall, both fuel treatment strategies effectively reduced wildfire hazard and should be part of a larger, holistic and integrated plan to reduce the vulnerability of the Alvares parish to wildfires.

The population dynamics of Hazel Grouse was studied by presence/ absence recording at stationary sites along fixed routes (110 km) during 1972-2019 in the central part of the Bohemian Forest (Šumava, Czech Republic). The 100-km² study area covered altitudes between 600 m (Rejstejn) and 1,253 m a.s.l., (mount Sokol). Our data base contained indices of Hazel Grouse occupancy: positive sites/ controlled sites for a yearly increasing number of Hazel Grouse occurrence sites (N = 134) for 48 years. We used a loglinear Poisson-regression method to analyze the long-term population trend for Hazel Grouse in the study area. In the period 1972 to 2006 we found a stable Hazel Grouse population (p = 0.83). From 2006-2007 to 2019, the population index dropped (-3.8% per year, p &lt; 0.05) for the last 13 years. This decline is assumed to be influenced by habitat loss due to succession resulting in older, more open forest stands, by strongly increasing forestry and windstorm “Kyrill” followed by clear cutting, bark-beetle damage, and removal of pioneer trees in spruce plantations, which diminished buds and catkins, the dominant winter food. The influence of disturbance by increasing touristic activities and/or predation is discussed. Our results could help to optimize conservation efforts for Hazel Grouse in the Bohemian Forest.

Carbon sequestration is associated with plant biomass and soils. The amount of carbon sequestration in the Atewa Range Forest Reserve (ARFR) is affected by varied anthropogenic activities like logging, mining and farming. This study estimate the above and below ground carbon stock and assess human-induced stress impacts on the Highly Stressed Vegetation (HSV), Moderately Stressed Vegetation (MSV), and Non-Stressed Vegetation (NSV) in the ARFR. The above ground biomass of trees was determined using the allometric model of (Henry, et al., 2010) whereas plants root biomass was calculated using Cairns et al. (1997). Soil organic carbon was determined using the Walkley–Black method. We observed that carbon stock was higher in the above-ground than the below-ground component. The MSV, recorded the highest stock of carbon followed by the NSV and the HSV whilst sequestrated carbon stocks was generally high and varied across the three stress levels. Within the forest, the intensity of anthropogenic activities has negatively impacted the amounts of carbon sequestrated at various levels.

Agricultural expansion is altering the provision of ecosystem services and seriously affecting the well-being of the indigenous communities still living in forests. In this paper, we evaluate the impact of forest loss and degradation on the indigenous forest dependent communities of Eastern Salta, Argentina, between 2001 and 2015. First, we identified the demand area of ten final ecosystem services for 202 indigenous communities using participatory mapping data. Second, we calculated the remaining usage area using a deforestation geodatabase based on Landsat images. Third, we analyzed the significance of trends in forest productivity processing vegetation spectral indices from MODIS products. By last, we detected changes in the growing season length by evaluating monthly trends in spectral indices. Our results show a reduction of 21% in the area used by indigenous communities for capturing final ecosystem services, and significant negative trends in forest productivity for the demand area of 64% of the communities, indicating that the area of use is not only being reduced, but also remnant forest area is being degraded and the growing season is being shortened. These aspects indicate an important loss in the provision of ecosystem services that deeply affects the wellbeing of indigenous communities.

Forest planners have traditionally used expected growth and yield coefficients to predict future merchantable timber volumes. However, because climate change affects forest growth, the typical forest planning methods using expected value of forest growth can lead to sub-optimal harvest decisions. We proposed in this paper to formulate the harvest planning with growth uncertainty due to climate change problem as a multistage stochastic optimization problem and use sample average approximation (SAA) as a tool for finding the best set of forest units that should be harvested in the first period even though we have a limited knowledge of what future climate will be. The objective of the harvest planning model is to maximize the expected value of the net present value (NPV) considering the uncertainty in forest growth and thus in revenues from timber harvest. The proposed model was tested on a small forest with 89 stands and the numerical results showed that the approach allows to have superior solutions in terms of net present value and robustness in face of different climate scenarios compared to the approach using the expected growth and yield. The SAA methods requires to generate samples from the distribution of the random parameter. Our results suggested that a sampling scheme that focuses on generating high number of samples in distant future stages is favorable compared to having large sample sizes for the near future stages. Finally, we demonstrated that, depending on the level of forest growth change, ignoring this uncertainty can negatively affect forest resources sustainability.

Forest plantations have a large potential for carbon sequestration, playing an important role in the global carbon cycle. However, despite the huge amount of research carried out worldwide, the absolute contribution of industrial forest plantations is still incomplete for some parts of the world. To contribute to bridge this gap, we calculated the amount of C stock in three fast growing forest species in Chile. Relevant C pools (above-ground and below-ground biomass, forest floor, and soil) were considered for this analysis. Across the industrial plantation forests of Chile, carbon accumulated in the above-ground biomass was 181–212 Mg · ha−1 for Pinus radiata, 147–180 Mg · ha−1 for Eucalyptus nitens, and 95–117 Mg · ha−1 for Eucalyptus globulus (age 20–24 years for P.radiata and 10–14 years for Eucalyptus). Our results agree with other studies showing that 30%–50% of the total C stock is stored in the soil. Total C stocks were for 343 Mg · ha−1 for P.radiata, 352 Mg · ha−1 for E.nitens, and 254 Mg · ha−1 for E. gloubulus, also at the end of a typical rotation. The carbon pool in the forest floor was found to be significantly lower (less than 4% of the total) when compared to the other pools and showed large spatial variability. We conclude that industrial forest plantations are a valuable tool to reduce atmospheric CO2 and mitigate climate change. Given the contribution of soils to total carbon stocks, special attention should be paid to forest management activities that affect the soil organic carbon pool.

Distinguishable annual growth rings produce in Pinus roxburghii are an asset to find out the age of individual tree. This paper aimed to determine the age of P. roxburghii through coring samples and test the relationship with forest production. The biomass estimated, girths measured at two different sections and heights measured which allowed to determine the rate of tapering of the stand. The regression analysis was performed to test the relationship between various variables. The mean age of the P. roxburghii stand was found to be 23.97 (~24 years). The result showed the significant (p<0.05) positive correlation coefficient has been seen between age with girth at breast height, biomass, volume and carbon stock. However, no significant (p>0.05) correlation (r = 0.08) was found between age and height of the stand. In contrast, a correlation between diameter at breast height (DBH) was significant (p<0.05) and positive with volume, biomass, but no significant (p>0.05) correlation (r = 0.14) found between DBH and height of the stand. However, height has a significant (p<0.05) positive correlation with biomass. The mean biomass was 375 kg and mean annual increment (MAI) was 15 kg per tree. Rate of tapering of the studied stand predicted to be 3 cm diameter decreased with trunk height running at 100 cm from base to upward of P. roxburghii stand and vice versa. Result suggests that height-age relation is very weak whereas age, DBH, biomass and carbon has a significant correlation signifies that time-based forests' production and potential production estimation can be obtained in a relatively accurate way by utilizing the age of stand. The time-based forest production analysis is pioneer work in Nepal. The study affirms the tree ring count in P. roxburghii would be a credible and accurate method to determine the age of standing trees.

Achieving sustainable management of forests in China is becoming increasingly important with more awareness and realization of the importance of forests in environmental protection. Forest certification, a market-based instrument to promote sustainable forest management, has been recognized by many countries including China. While landowners’ perception and perspective regarding this voluntary program have been well-documented in literature, how to motivate and incentivize landowners to participate in forest certification remained under-studied questions. With the face-to-face survey of landowners in Shandong, China, this study analyzed landowners’ willingness to accept compensation for participating in forest certification. Results indicated that landowners average accepted compensation, in terms of increased timber price, was about RMB120 (~$17.2)/m3 to have their forests certified. Results from multiple regression showed that the level of such compensation required for certification adoption was influenced by ownership size, owners’ demographics, certification program requirements, as well as importance placed on timber sale. These findings would inform policy-makers in designing compensation-related polices and establish incentive-based mechanisms to motivate landowners participate in forest certification programs in China.

Landslides impact on human activities and socio-economic development especially in mountainous areas. This study focuses on the comparison of the prediction capability of advanced machine learning techniques for rainfall-induced shallow landslide susceptibility of Deokjeokri catchment and Karisanri catchment in South Korea. The influencing factors for landslides i.e. topographic, hydrologic, soil, forest, and geologic factors are prepared from various sources based on availability and a multicollinearity test is also performed to select relevant causative factors. The landslide inventory maps of both catchments are obtained from historical information, aerial photographs and performing field survey. In this study, Deokjeokri catchment is considered as a training area and Karisanri catchment as a testing area. The landslide inventories content 748 landslide points in training and 219 points in testing areas. Three landslide susceptibility maps using machine learning models i.e. Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) are prepared and compared. The outcomes of the analyses are validated using the landslide inventory data. A receiver operating characteristic curve (ROC) method is used to verify the results of the models. The results of this study show that the training accuracy of RF is 0.757 and the testing accuracy is 0.74. Similarly, training accuracy of XGBoost is 0.756 and testing accuracy is 0.703. The prediction of DNN revealed acceptable agreement between susceptibility map and the existing landslides with training and testing accuracy of 0.855 and 0.802, respectively. The results showed that, the DNN model achieved lower prediction error and higher accuracy results than other models for shallow landslide modeling in the study area

Forests across the world stand at the crossroad with climate and land use changes shaping their future. Despite the demonstration of political will and global efforts, forest loss, fragmentation and land degradation continue unabated. No clear evidence exists that these initiatives are working. Why are policies designed to halt deforestation and increase restoration of forest landscapes failing? A key reason for this apparent ineffectiveness lies in the failure to recognize the agency of the stakeholders involved and the adaptive capacities of the systems we seek to steer. Landscapes do not happen. We make them. They are the result of the sum of individual actions and decisions made by all stakeholders, and the interactions between these and biophysical processes. Likewise, forest transitions are not ecological, but social and behavioral. They are a product of the way humans manage ecosystems. Decision-makers need to integrate better representations of people’s agency in their mental models. We suggest possible solution pathways to overcome this key current barrier. These involve eliciting mental models behind policy decision, changing perspectives to better understand divergent points of view and refining strategies through explicit theories of change. Games designed to represent the constraints and opportunities that exist in the landscapes can help decision makers in these task.

Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized R-R intervals and features relative to the width of the QRS complex are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats respectively. In comparison with other state of the art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

Accurate prediction of defects in software components plays a vital role in administrating the quality of the quality and efficiency of the system to be developed. So we have written a systematic literature review in order to evaluate the four main defect prediction techniques. Defect prediction paves way for the testers to find bugs and modify them in order to achieve input to output conformance. In this paper we have discussed the open issues in predicting software defects and have provided with a detailed analyzation of different methods including Machine Learning, Integrated Approach, Cross-Project and Deep Forest algorithm in order to prevent these flaws. However, it is almost impossible to rule which method is better than the other so every technique can be analyzed separately and the best technique according to the problem at hand can be used or can be altered to create hybrid technique suitable for the cause.

In this study, the decision-making process management of forest tending in the forestry business is decentralized, and forest tending decision-making activities at different points in time are integrated by decision makers at different geographical locations. The decision-making process was analyzed and optimized from a system perspective. Based on the optimized decision-making process, a forest tending business group decision support system (FTGDSS) was established. We first reviewed and discussed the characteristics and development of the forest tending business and forestry decision support system. Business Process Modeling Notation was used to draw a current state flow chart of the forest tending business, to identify and discover important decision points in the process of tending decision-making. We also analyzed the content and attributes of each decision point, and described the system structure, functional framework, knowledge base structure, and reasoning algorithm of FTGDSS in detail. Finally, FTGDSS was evaluated from the two dimensions of the technology adoption model. FTGDSS integrates different levels of time-space decision-making activities, historical tending data, business plans, decision-makers' management tendencies into the decision-making process and automatically extracts decision-making data from the forest business process management enterprise resource planning system (Smartforest) that improves the ease of use of the decision support system (DSS). It also improves the quality of forest tending decisions, and enables the DSS to better support multi-target management strategies.

Abstract: Research Highlights: This study is among the first to investigate ozone levels in urban forests in China. It establishes that urban forest air quality in Yuanshan Forest Park, Shenzhen, is suitable for recreational activities and identifies spatial, seasonal, and diurnal O3 patterns and relationships with micrometeorological parameters, suggesting the possibility of manipulating relevant forest characteristics to reduce O3 levels. Background and Objectives: An understanding of O3 levels of urban forest environments is needed to assess potential effects on human health and recreational activities. Such studies in China are scarce. This study investigated urban forest O3 levels to improve understanding and support residents engaging in forest recreational activities. Materials and Methods: We monitored O3 levels in 2015–2016 for three urban forests representing common habitats (foothill, valley, and ridge) in Yuanshan Forest Park, Shenzhen, and for an adjacent square. Results: The overall mean daily and daily maximum 8-h mean (MDA8) O3 concentrations were highest for the ridge forest and lowest for the valley forest. Each forest’s O3 concentrations were highest in summer. Diurnally, forest O3 concentrations peaked between 13:00 and 17:00 and reached a minimum between 03:00 and 09:00. The correlation between forest O3 concentrations and air temperature (AT) was strongly positive in summer and autumn but negative in spring. In each season, O3 concentration was negatively correlated with relative humidity (RH). No MDA8 or hourly O3 concentrations in the forests exceeded National Ambient Air Quality Standard Grade I thresholds (100 and 160 μg m−3, respectively). Conclusions: O3 accumulation is present in ridge urban forest in all seasons. Foothill and valley urban forests have better air quality than ridge forestation. Urban forest air quality is better in spring and autumn than in summer and is better from night-time to early morning than from noon to afternoon.

Open pit mining is a common activity in the Yucatan peninsula for the extraction of limestone. This mining is known under the generic name of quarries, and regionally as sascaberas (sascab=white soil in Mayan language). These areas are characterized by the total removal of the natural vegetation cover and soil in order to have access to the calcareous material. The present study shows the composition and structure of the vegetation in five quarries after approximately ten years of abandonment, and the conserved vegetation near to each one of the quarries in southeastern Quintana Roo. Using a canonical correspondence analysis (CCA), the distribution of the species was determined in relation to the edaphic variables: soil depth, percentage of organic matter (OM), cationic exchange capacity (CEC), pH and texture. 26 families, 46 genera and 50 species were recorded in the quarries and 25 families, 45 genera and 47 species were recorded in the conserved areas. The dominant species in the quarries belong to the families Poaceae, Fabaceae, Rubiaceae and Anacardiaceae. The quarries with higher values of OM (1.63%), CEC (24.05 Cmol/kg), depth (11 cm) and sand percentage (31.33%) include the following species like Lysiloma latisiliquum, Metopium brownei and Bursera simaruba which are commonly found in secondary forests. On the other hand, quarries with lower values of OM (0.39%), CEC (16.58 Cmol/kg) and depth (5.02), and higher percentage of silt (42.44%) were dominated by herbaceous species belonging to the Poaceae family and by Borreria verticillata, which are typical in disturbed areas of southeastern Mexico. In all cases, the pH was slightly alkaline due to the content of calcium carbonate (CaCO3), characteristic of the soils of the region. The edaphic variables are significantly correlated with the development and distribution of vegetation, and with the structure of the communities.

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

Research Highlights: The study determined that selective thinning causes different responses, the initial size of the tree released is an influential factor in the growth of species. The temporality of climate and physiological conditions of each species are influential in the growth. It is evident that the defoliation of certain species is an important factor that limits the growth of the species causing thinning to have a negative response. Background and Objectives: The objective is to analyze the behavior of nine timber species, respective to diametric growth after their liberation. This research aims to answer the following questions: (i) How do the selected tree species react to the liberation? (ii) Can the productivity of the trees (diametric growth) be enhanced by liberation? (iii) Are there other factors that influence the diametric growth of the released trees? Materials and Methods: The study was executed in the “Reserva Biológica San Francisco” were 488 trees were monitored, including nine timber species. Therefore, 197 trees were released (removal of competitors) and 251 trees served as reference. To check whether the initial DBH or other factors, like the selective thinning or climate conditions, determine the diameter growth a linear mixed model GLMM was applied. To adjust the linear mixed model a one-way Anova test was executed. Results: Timber species responded differently to the thinning in comparing to reference trees. Therefore, the species analyzed were separated into three groups (positive, negative, and no response to liberation). Conclusions: Liberation potentiates the growth of certain timber species that do not defoliate and considered semi-tolerant to shade. Precipitation and temperature affect all species, but in the defoliate species, it would not be convenient to release them or at least the evidence of these first three years does not show clear differences with control trees. Increase in trees released are higher in trees of the first two diametric classes in all species, this means that larger trees (i.e., older) release does not affect them in a positive way so release should occur in the youngest trees.

Incidental P losses from non-point sources may contribute to eutrophication and to decreased soil fertility. These incidents have been related to heavy rainfall on freshly fertilized agricultural soils and little is known about such incidents on more natural soils or in forests. The aim of this work is to determine if incidents of high P leaching also occur in spruce forests, and if such incidents are of significance in P cycling. We found a peak in the mineral soil solution showing that single events of high P leaching occur. The orthophosphate concentration in the Bf-horizon of the 80-year old spruce forest peaked in the autumn of the second year of a continuous monitoring. The concentration increased by more than 85 times compared to the highest concentration obtained earlier during the sampling. The amount leached during this 6 months peak is 10 times higher than the average annual leaching. This P leaching might be due to a combination of high P deposition/through-fall and a high anion exchange with dissolved-organic-carbon and Cl-. We suggest that single events of high sub-surface P leaching may contribute to the overall P leaching, and might increase with the global warming as more DOC is expected to be released to the soil solution.

Understanding ecological interactions is a key in managing phytopathology. Although entomologists rely mostly on both traditional molecular methods and morphological characteristics to identify pests, next-generation sequencing is becoming the go-to avenue for scientists studying fungal and oomycete phytopathogens. These organisms sometimes infect plants together with insects. There are many relationships yet to be discovered and much to learn about how these organisms interact with one another. Considering the growing number of exotic insect introductions in Canada, a high-throughput strategy for screening those insects is already implemented by the Canadian Food Inspection Agency (CFIA). However, no plan is deployed to investigate the phytopathogenic fungal and oomycete species interacting with insects. Metagenomics analysis was performed on the preservation fluids from CFIA’s insect traps across Canada. Using the Ion Torrent PGM technology and fusion primers for multiplexing and indexing, community profiling was conducted on the different semiochemicals used in the insect traps and the various areas where these traps were placed. Internal transcribed spacer 1 (fungi and oomycetes) and adenosine triphosphate synthase subunit 9-nicotinamide adenine dinucleotide dehydrogenase subunit 9 spacer amplicons were generated. Although direct links between organisms could not be established, moderately phytopathogenic fungi (e.g., Leptographium spp. and Meria laricis) and oomycetes (mainly Peronospora spp. and Pythium spp.) unique to every type of semiochemical were discovered. The entomopathogenic yeast Candida michaelii was also detected. This project demonstrated our ability to screen for unwanted species faster and at a higher scale and throughput than traditional pathogen diagnostic techniques. Additionally, minimal modifications to this approach would allow it to be used in other phytopathology fields.

Pinus patula is one of the most planted wood conifer species worldwide; however, no foliar nutrient standards exist for this species up to date. The objective of the present study was to generate and verify two sets of foliar nutrient standards for nearly ten-year-old P. patula trees: critical nutrient concentrations and DRIS norms. Nutrients studied were N, P, K, Ca, Mg, Fe, Cu, Zn, Mn, and B. The reference standards were verified experimentally by installing two fertilization trials; one of them located in Huayacocotla, state of Veracruz and the other one in Aquixtla, state of Puebla, Mexico. Nutrient status of each fertilization trial was correctly predicted by critical nutrient values and DRIS as well. Both standards were able to detect the secondary growth-limiting nutrient deficiency in the Huayacocotla trial, where the primary limitation for growth was scarcity of solar radiation within tree crowns. The limiting nutrient in both experimental trials was K.

This study proposes a novel hybrid machine learning approach for modeling of rainfall-induced shallow landslides. The proposed approach is a combination of an instance-based learning algorithm (k-NN) and Rotation Forest (RF), state of the art machine techniques that have seldom explored for landslide modeling. The Lang Son city area (Vietnam) is selected as a case study. For this purpose, a spatial database for the study area was constructed, and then, was used to build and evaluate the hybrid model. Performance of the model was assessed using Receiver Operating Characteristic (ROC), area under the ROC curve (AUC), success rate and prediction rate, and several statistical evaluation metrics. The results showed that the model has high performance with both the training data (AUC = 0.948) and the validation data (AUC = 0.848). The results were compared with those obtained from soft computing techniques i.e. Random Forest, J48 Decision Trees, and Multilayer Perceptron Neural Networks. Overall, the performance of the proposed model is better than those obtained from the above methods. Therefore, the proposed model is a promising tool for landslide modeling. The research result can be highly useful for land use planning and management in landslide prone areas.

By introducing environmental mediator, for avoiding randomness in selecting indicators and subjectivity in deciding interaction path coefficients to reveal interaction mechanism among forest industry, ecology and environmental capacity, structural Pressure–State–Impact–Response (PSIR) and quantitative Structural Equation Modeling (SEM) are utilized with data on thirty–one provinces of China. We can find that: (i) forest industry has a negative influence on ecology, whereas ecology has a positive influence on industry; (ii) the destructive influence that industry has on ecology is much greater than the positive effect ecology has on industry; and (iii) environmental capacity plays a partial mediating role between industry and ecology. According to these results we can conclude that: (i) forest industry and ecology are not in a symbiotic relationship and have not reached a level of ecological security; (ii) the interaction between industry and ecology is in a period of transition from antagonistic to beneficial; and (iii) industry dominates ecology. However, we prospect the following advice: (i) methods of forest industry should be changed; (ii) new modes of industrial integration and circular economy should be developed; and (iii) the ability of the environment to sustain itself should be enhanced. The level of forest ecological security to discuss the symbiotic mechanism of industry and ecology will propose to be measured in future.

Customer churn is a critical challenge for subscription-based businesses, especially in telecommunications, where retaining customers is essential to maintaining profitability. This study investigates the efficacy of two ML models, XGBoost and Random Forest, for predicting customer churn using a publicly available telecommunications dataset. The dataset, characterized by imbalanced classes, presents a crucial challenge addressed by incorporating the Gaussian Noise Upsampling (GNUS) sampling technique. The study evaluates and compares the two models using essential performance indicators, including precision, recall, accuracy, F1-score, and ROC-AUC, both with and without GNUS sampling. The results indicate that while XGBoost initially outperforms Random Forest across most metrics, both models show improved recall after the GNUS application, particularly in identifying churn cases. However, this improvement in recall comes with a trade-off in precision and overall accuracy. The findings highlight the relevance of using appropriate sampling techniques to tackle class imbalance in churn prediction and provide valuable insights for developing proactive customer retention strategies.

The government of Laos has made significant efforts to halt deforestation and promote forest conservation in the Northern Uplands of Laos. However, there is no comprehensive assessment of the initiatives and factors that influence youth involvement in forest resource conservation. Our goal was to find sustainable forest management practices and understand the factors affecting young people's behaviors related to forest conservation. We conducted our study in 3 districts, covering 15 villages. We used multiple regressions to identify the factors influencing sustainable forest management behaviors, involving 330 youths who were systematically and randomly selected to participate in structured interviews. Our results showed that conservation knowledge and recognition are associated with demographic and socioeconomic factors, especially education. Factors related to forest conservation recognition included the amount of information available, gender, monthly income, land ownership, and distance from the forest to home. Most households rely on forest products for their livelihoods. We found that higher levels of education provide people with more job opportunities, which improves their job status and quality of life. Community members who received relevant information were more forward-thinking in their forest management behaviors and willing to contribute to related activities. Providing essential information to young people can help improve sustainable forest management behaviors.

Litter decomposition is a crucial biochemical process regulated by microbial activities in forest ecosystem. However, the dynamic response of fungal community during litter decomposition to vegetation changes is not well understood. Here, we investigated the litter decomposition rate, extracellular enzyme activities, fungal community, and nutrient cycling-related genes in leaf and twig litters over a three-year decomposition period in a pure Liquidamabar formosana forest and a mixed L. formosana / Pinus thunbergii forest. The result showed that during the three-year decomposition, twig litter decomposed faster in the mixed forest than that in the pure forest. In both leaf litter and twig litter, β-cellobiosidase, N-acetyl-glucosamidase exhibited higher activities in the mixed forest, whereas phosphatase, β-glucosidase and β-xylosidase were higher in the pure forest. The fungal α-diversity were higher in both litters in the pure forest compared to mixed forest, with leaf litter showing higher α-diversity than twig litter. Fungal species richness and α-diversity within leaf litter increased as decomposition progressed. Within leaf litter, Basidiomycota dominated in the mixed forest while Ascomycota dominated in the pure forest. Funguild analysis revealed that symbiotroph and ectomycorrhizal fungi were more abundant in the mixed forest compared to the pure forest. In the third-year decomposition, genes related to phosphorus cycling was most abundant in both forests, with the pure forest having a higher abundance of cex and gcd genes. Fungal community structure, predicted functional structure, and gene composition differed between the two forest types and between the two litter types. Notably, the fungal functional community structure during the first-year decomposition was distinct from that in the subsequent two-year. These findings suggest that both dominant tree species, litter quality and decomposition time significantly influence the litter decomposition by recruiting different fungal community, thereby affecting the entire decomposition process.

Differentiated thyroid cancer (DTC), comprising of papillary and follicular thyroid cancers, is the most prevalent type of thyroid malignancy. Accurate prediction of DTC is crucial for improving patient outcomes. Machine learning (ML) offers a promising approach to analyze risk factors and predict cancer recurrence. In this study, we aimed to develop predictive models to identify patients at an elevated risk of DTC recurrence based on 16 risk factors. We developed six ML models and applied them to a DTC dataset. We evaluated the ML models using Synthetic Minority Over-Sampling Technique (SMOTE) and with hyperparameter tuning. We measured the models’ performance using precision, recall, F1 score, and accuracy. Results showed that Random Forest consistently outperformed the other investigated models (KNN, SVM, Decision Tree, AdaBoost, and XGBoost) across all scenarios, demonstrating high accuracy and balanced precision and recall. The application of SMOTE improved model performance and hyperparameter tuning enhanced overall model effectiveness.

Machine learning methods used for classification can face challenges due to class imbalance, where a certain class is underrepresented. Over/under-sampling of minority/majority class observations, or model selection for ensemble methods alone, may not be effective if the class imbalance ratio is very high. To address this issue, this paper proposes a method called enhance tree ensemble (ETE) based on generating synthetic data for minority class observations in conjunction with tree selection based on their performance on the training data. The proposed method first generates minority class instances to balance the training data and then uses the idea of tree selection by leveraging out-of-bag (〖ETE〗_OOB) and sub-samples (〖ETE〗_SS) observations, respectively. The efficacy of the proposed method is assessed using twenty benchmark problems for binary classification with moderate to extreme class imbalance, comparing it against other well-known methods such as optimal tree ensemble (OTE), SMOTE random forest (〖RF〗_SMOTE), over-sampling random forest (〖RF〗_OS), under-sampling random forest (〖RF〗_US), k-nearest-neighbor (k-NN), support vector machine (SVM), tree, and artificial neural network (ANN). Performance metrics such as classification error rate and precision are used for evaluation purposes. The analyses of the study revealed that the proposed method, based on data balancing and model selection, yielded better results than the other methods.

Baijiu is popular with its long history and balanced flavor, and flavor type was the most widely used classification mode for Baijiu. However, the evolution relationship of Baijiu flavor types and the differential markers between flavor types are still unclear, which has greatly affected the development of Baijiu industry. In this study, a total of 319 trace components were identified by gas chromatography-olfactometry-mass spectrometry and gas chromatography-mass spectrometry. Among them, 91 trace components with high odor active values or taste active values were recognized as flavor components. Then random forests were conducted to screen differential markers between derived and basic flavor types, and principal component analysis was carried out to evaluate their effectiveness in distinguishing the flavor types of Baijiu. Finally, 19 differential markers were screened and proved to effectively reveal the evolution Baijiu flavor types, and were further verified as key differential markers by addition test and correlation analysis.

Co-management is increasingly recognized as an effective approach of forest governance while recognizing local people's forest dependency and traditional rights. Moreover, co-management is expected to positively impact forest cover and ecosystem health. Bangladesh, facing a rapid decline in forest cover, has one of the lowest per capita forest areas worldwide. For quite a while, co-management practices have been used to improve forest cover and the livelihoods of forest-dependent people in Bangladesh. Several studies have assessed the efficacy of co-management in different protected areas in Bangladesh from livelihood, social, and cultural aspects. However, the overall changes in forest cover due to co-management from the very beginning of co-management initiatives in the country have been overlooked. We used remotely sensed Landsat images to assess the changes in forest cover and overall land use in five forest protected areas where co-management was piloted. Three major vegetation indices (NDVI, EVI, and MSAVI) were examined to ensure the study's robustness. This study aims to assess the scope and weaknesses of the current policy that incorporates co-management in the country's first five protected areas (SNP, LNP, RKWS, TWS, and CWS), which were brought under co-management in 2003, and compare the efficacy of the co-management relative to non-comanaged protected areas (RRF). The land cover analysis based on NDVI, MSAVI, and EVI values indicated dominant dense forest coverage (41–71%) across five protected areas. During the co-management period (2004–2015), there was a significant decrease in the dense forest proportion, with slopes ranging from -3.7 to -0.96. Similarly, the RRF showed a decreasing pattern, with the slope of the decreasing trendline ranging from -0.48 to -0.62 across the three indices. Agriculture and forest-agriculture mosaics showed a significant increase, with varying slopes among protected areas in both co-managed and non-comanaged sites. Pixel-to-pixel changes revealed dynamic shifts in vegetation indices, and Global Forest Watch data highlighted forest cover losses, notably in CWS (158.77 ha) and SNP (0.49 ha).

Invasive species are one of the five main causes of biodiversity loss, along with habitat destruction, overexploitation, pollution, and climate change. Represent one of the first barriers to overcome in ecological conservation programs, since are difficult to control and eradicate. Due to the lack of records of invasive exotic species in Panama, this research is necessary to identify and register the documented groups of invasive species of the Chordates and Arthropod groups in Panama. This exhaustive search of invasive species was carried out in different bibliographic databases, electronic portals and scientific journals which addressed the topic at a global level. The results indicate that approximately 133 invasive exotic species of the Arthropoda and Chordata Phylum have been reported in Panama. Of the 133 species, 49 species belong to the Arthropoda Phylum and 84 species belong to the Chordate Phylum. The Panamanian economic activity could promote the introduction of alien species in this country. The study provides the first list of invasive exotic chordate and arthropod species reported for the Republic of Panama.

This article explores the application of machine learning techniques, specifically focusing on ensemble methods like Random Forests, for detecting fraudulent activities in digital financial transactions. Highlighting the evolution from traditional statistical approaches to modern machine learning models, it underscores the effectiveness of Random Forests in handling the inherent challenges of imbalanced datasets typical in fraud detection scenarios. Using a Kaggle dataset of credit card transactions, the study optimizes Random Forest parameters through rigorous parameter tuning, achieving significant improvements in model performance metrics such as Area Under the Curve (AUC). The findings underscore the critical role of machine learning in enhancing fraud detection capabilities, emphasizing the ongoing evolution and future potential of these methodologies in financial risk management.

Increased anthropogenic pressure on forest resources leads to deforestation and forest degradation, significantly limiting the regeneration capacity of native woody species and consequently the restoration of miombo woodlands in anthropized habitats within the rural area of Lubumbashi. This study assessed the diversity and natural regeneration capacity of miombo species through floristic inventories in three different habitats (unexploited forests, degraded forests, and post-cultivation fallows). The results reveal that for the adult’s stratum unexploited and degraded forests exhibit higher dendrometric (density, mean square diameter, basal area) and floristic parameter (taxa, genera, families) values compared to post-cultivation fallows. Furthermore, the regeneration of miombo woody species is higher in degraded forests (21 taxa; 105 juveniles/plot). However, regarding the sapling’s stratum (1 cm ≤ dbh &lt; 10 cm), the three habitats display nearly similar situations. Additionally, the floristic composition and diversity of unexploited and degraded forests show a significantly higher similarity (76.50%) among them compared to these habitats and the post-cultivation fallows (56.00%). These findings indicate that miombo woodlands have the potential to regenerate and maintain floristic diversity. To sustain this natural regeneration capacity of miombo woody species and promote the restoration of forest mass and its floristic diversity, it is imperative to determine the rotation period after habitat exploitation and regulate anthropogenic activities and late bush fires, particularly in anthropized habitats at the village level.

As a precious natural resource, forests are being destroyed. In previous studies, there is a lack of interactive assessment of its distribution that comprehensively considers multiple external disturbances. This paper takes the Barcelona Metropolitan Region as an example. Based on remote sensing, it analyzes the development process of the forest from 2006 to 2018 through multiple landscape indicators, and OLS models were established to analyze variables that have direct and indirect effects on forest distribution. In addition, the ecological structure of the forest was analyzed based on NDVI. It was found that the forest area is the largest but has been decreasing, becoming more complex in distribution structure. Much of the forest was converted to agricultural land and grassland. The green quality of forests was increasing, and the broad-leaved forest, the second largest area, contributes the most. NDVI is the most important positively correlated variable, and daytime surface temperature is an important inverse factor related to NDVI. In addition, NDBI is also a negative condition that inhibits forest development. In conclusion: The BMR forest area is decreasing and becoming more fragmented. NDVI and daytime LST are the two most significant factors. Climate warming may lead to worse forest development.

In recent years, long periods of drought and heat waves have become increasingly frequent, causing forest dieback phenomena that make stands more sensitive to biotic stressors. How trees may respond to extreme climatic events and which metabolites are involved under stress conditions is still not clear. In this study, we analysed by SPME how dieback (D) and non-dieback (ND) Hungarian oak trees from the San Paolo Albanese site respond to these climatic dynamics, in terms of volatile organic compounds (VOCs). For each group of trees, three wood samples were taken, each divided into four sub-samples with 5 growth rings, subjected to SPME and increase in basal area (BAI) analysis of the last 20 years. Dieback trees had a lower amount of leaves, and this condition may translate into less photosynthesis, less organic matter production and lower reserves of carbohydrates available for growth. Indeed, D trees showed lower radial increases and a lower content of aldehydes, terpenes, and fatty acids than ND trees, indicating a better health of ND trees compared to D trees. While D trees showed a reduction in terpenes, such as α-pinene, γ-eudesmol, and cyperene (with significant insecticidal activity), a reduction in aromatic aldehydes, such as furfural and 5-methylfurfural, and an increase in silanols (with antimicrobial function). Considering the different compounds’ contents between D and ND trees, our study could be useful for detecting bio-indicators to identify an early warning signal of dieback phenomena.

This paper explores the role of agroforestry in mitigating climate change by sequestering atmospheric carbon in the tropics and subtropics, specifically in the Madhupur Sal forest of Bangladesh. Agroforestry, combining trees with crops on agricultural lands, is recognized for its potential to act as carbon sinks and enhance productivity. The study assesses various agroforestry practices, including Acacia-Pineapple-Turmeric-Papaya, Acacia-Pineapple-Zinger-Banana, and Sal-Pineapple-Aroid combinations. The research reveals improved farm productivity in these agroforestry systems, with different tree species sequestering varying amounts of carbon. Acacia species, ranging from 12 to 25ft in height, sequestered an average of 23.35 lbs/year, while Sal species (Shorea robusta), with trees 45 to 61ft tall, sequestered 49.80 lbs/year on average. Factors such as tree height, diameter at breast height (DBH), number of leaves, and branches influence carbon sequestration. The paper suggests integrating the carbon trading system of the Clean Development Mechanism (CDM) with Carbon Sequestration (CS) potential to leverage agroforestry for greenhouse gas emission reduction in Bangladesh. By emphasizing the profitability of these practices alongside carbon sequestration, the study encourages the adoption of agroforestry as a sustainable and economically viable strategy for climate change mitigation.

Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffer from poor generalization ability in presence of dataset shift. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black-box model (Random Forest), both studied with the aim to support clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.

Precise individual tree or sample-based inventories derived from 3D point cloud data of mobile laser scanning can improve our comprehensive understanding of the structure, function, resilience, biodiversity, and ecosystem services of urban forests. This study assessed the performance of a hand-held laser scanning system for the extraction of tree position, diameter at breast height (DBH) and tree height (H) in an urban area. A total of 2083 trees of 13 species from 34 plots were analyzed. The results showed that the registration of tree positions using ground control points (GCPs) demonstrated high accuracy, with errors consistently below 0.4 m, except for a few instances. The extraction accuracy of DBH for all trees and individual species remained consistently high, with a total root mean square error (RMSE) of 2.06 cm (6.89%) and a bias of 0.62 cm (2.07%). Notably, broad-leaved trees outperformed coniferous trees, with RMSE and bias values of 1.86 cm (6%) and 0.76 cm (2.46%) compared to 2.54 cm (9.46%) and 0.23 cm (0.84%). Tree height extraction accuracy varied significantly among different species, with R2 values ranging from 0.65 to 0.92. Generally, both DBH and height were underestimated. Linear mixed effects models (LME) were applied to evaluate factors affecting the performance of HLS with the plot as a random factor. LME analysis revealed that plant type and terrain significantly influenced the accuracy of DBH and H derived from HLS data. Other fixed factors of plot area, tree density and trajectory length didn’t have significance. With a large sample size, we concluded that the HLS demonstrated sufficient accuracy in extracting individual tree parameters in urban forests.

Abstract: Community forests are being promoted in Togo as an alternative to the degradation of protected areas and as a means of restoring forest landscapes. The present study is carried out within Kouampante Community Forest (KCF) in Ogaro (Togo, West Africa). It intends to contribute to the sustainable management of KCF. Specially, it aims at: (i) mapping forest ecosystems and analysing their dynamic and (ii) characterising the floristic diversity of the KCF. Forest ecosytems are mapped and their dynamic evaluated based on Google Earth images of 2010 and 2020. The floristic and silvicultural analyses are based on inventories carried out in 13 plots of 1,000 m² each. The KCF is made up mainly by tree/shrub savannahs (58.73%) and croplands/fallow (41.27%) in 2010. These two land use types have undergone changes over the period. In 2020, the KCF had two land use types: tree/shrub savannahs (84.30%) and croplands/fallows (15.70%). The flora census consisted of 59 species grouped in 6 families. The most important plant species are Detarium microcarpum and Vitellaria paradoxa. The Fabaceae were the most abundant and diversified families, followed by the Combretaceae. The demographic structure showed a high abundance of individuals with small diameter and height. This indicates the possibility of a rapid restoration of the native vegetation. Protecting the forest from anthropogenic threats could be crucial for achieving the desired objective.

The TROPOMI XCH4 data product requires rigorous cloud filtering to achieve a product accuracy of &lt;1%. To this end, the operational XCH4 data processing has been based on SUOMI-NPP VIIRS cloud observations. However, SUOMI-NPP is nearing at the end of its operational life and has encountered malfunctions in 2022 and 2023. In this study, we introduce a novel machine learning cloud clearing approach based on a random forest classifier (RFC). The RFC is trained on collocated TROPOMI and SUOMI-NPP VIIRS data to emulate VIIRS-like cloud clearing. After training, cloud masking requires only TROPOMI data, and so becomes operationally independent of SUOMI-NPP. We demonstrate the RFC approach by applying cloud clearing to operational TROPOMI XCH4 data for August 2022, a period in which VIIRS was not operational. For validation, we analyze the TROPOMI XCH4 data at 12 TCCON stations. Comparison of cloud clearing using the RFC and the original VIIRS method reveals excellent agreement with a similar station-to-station bias (-7.4 ppb versus -5.6 ppb), a similar standard deviation of the station-to-station bias (11.6 ppb versus 12 ppb), and the same Pearson correlation coefficient of 0.9. Remarkably, the RFC cloud clearing provides a slightly higher volume of data (2182 versus 2035 daily means) and appears to have fewer outliers. Since November 21, 2023, the RFC approach is part of ESA’s operational processing chain. For now the default practice is to utilize SNPP-VIIRS when accessible. Only in cases where VIIRS data is unavailable do we resort to the RFC cloud mask.

The overwhelming evidence supports the assertion that the climate is undergoing change. Understanding the perception of locals of the magnitude of climate change and its influence on non-timber forest products (NTFPs) challenge at a global scale. Although studies on climate change, value addition, and the multiple uses of NTFPs and their impact on local livelihoods have been conducted, locals' perceptions of these factors have not been fully explored. This study aims to assess various social factors, including education, gender, and religion, and their influence on locals' perceptions of the abovementioned factors. The research focused on five regions where NTFPs are prevalent in Ghana (Western North, Bono, Ahafo, Ashanti, and Eastern regions). To investigate the impact of social factors on local perceptions of climate change, value addition, and the multiple values of NTFPs within rural communities, a total of 732 interviews with a team of interviewers across these five regions in Ghana were carried out. We applied a logistic regression model to assess the social factors and their influencing locals’ perceptions of the mentioned variables. It was revealed that age, gender, education, and occupation did not significantly influence locals' perceptions of climate change. However, religion was found to influence locals' perceptions of climate change. Furthermore, the results demonstrated that gender (P<0.000328) and education (P<0.00426) strongly influenced locals' perceptions of value addition to NTFPs. In contrast, religion and constraints (related to time, finance, and skills) did not significantly influence locals' perceptions. Additionally, it was observed that gender (0.00132), education (0.00692), and religion (8.12e-05) significantly influenced how locals perceive and use NTFPs. In conclusion, this study provides valuable insights into the intricate interplay among local perceptions, climate change, value addition, multiple uses of NTFPs, and the capacity of NTFPs to enhance the well-being of forest fringe communities. These findings underscore the importance of comprehensive, tailor-made interventions that consider local perspectives and adhere to sustainable approaches, with the aim of optimising the positive impacts of NTFPs in poverty alleviation and overall community development.

Multispectral and 3D LiDAR remote sensing data sources are valuable tools for characterizing the 3D vegetation structure and thus understanding the relationship between forest structure, biodiversity and microclimate. This study focuses on mapping riparian forest species in the canopy strata using a fusion of Airborne LiDAR data and multispectral multi-sources and multi-resolution satellite imagery; Sentinel-2 and Pleiades at tree level. The idea is to assess the contribution of each data source in the tree species classification at the considered level. The data fusion was processed at feature-level and decision level. At feature level, LiDAR 2D attributes were derived and combined with vegetation indices. At decision level, LiDAR data was used for 3D tree crown delimitation providing unique trees or groups of trees that are used as a support for the species classification. Data augmentation techniques were used to improve the training process. Best results were obtained by the fusion of Sentinel-2 time series and LiDAR data with a Kappa of 0.66 thanks to red-edge based indices that better discriminate vegetation species and the temporal resolution of Sentinel-2 images that allows monitoring the phenological stages helping to discriminate the species.

Hyperspectral anomaly detection is to recognize anomalies from complex scene in an unsupervised way. Currently, many spectral-spatial detection methods have been proposed with a cascaded manner. However, they often neglect complementary characteristics between spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral-spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets prove that the proposed SSIF produces superior detection result over other state-of-the-art detection techniques.

Trees, often referred to as the "lungs of the Earth," hold immense significance for both the natural world and human society. Their contributions span a multitude of ecological, environmental, economic, and social domains, making them essential components of a healthy and thriving planet. Phytoplasma association not only compromise tree aesthetics but also reduce photosynthetic capacity and overall vigour. Phytoplasma diseases also lead to increased tree mortality, altering ecosystem dynamics.This review article provides an in-depth exploration of phytoplasma diseases affecting trees worldwide, encompassing their epidemiology, symptomatology, impact and management strategies.

For the territory of the Republic of Tatarstan (Russia), a spatial model of forest communities was built as a basis for assessing the sequestration potential of ecosystems. Combination of multi-temporal and multi-spectral satellite imagery from the Landsat 8 and Landsat 9 platform as input data and Google Earth Engine cloud platform were used. The set of 292 vegetation indices and metrics computed from the pre-processed imagery, were combined into dataset. The Weka X-Means clustering algorithm was trained and applied to study area. The unsupervised classification was carried out by vegetation classes in the Braun-Blanquet system. The results of unsupervised classification were verified using data from more than 17,000 relevés with geographic references from the Flora database. For automatic classification, the EuroVeg Checklist expert system in the JUICE 7.1 package was used. The proposed methodology for obtaining initial data and unsupervised classification, supported by an automated expert system, made it possible to obtain a picture of the vegetation distribution in the study area with sufficient accuracy, and in the future, it will be used to assess the sequestration potential of the ecosystems of the region under study.

Deforestation brings vast and detrimental impact on the environment, economy, and social aspects of community. Thus, it is important to assess and analyze deforestation to inform the decision maker that oversees issued policy and development strategies. The present study aims to characterize deforestation in Central Kalimantan between 2006 - 2020. Utilized land cover map issued by Indonesian Ministry of Environment and Forestry, we analyzed the change in natural forest cover using Remote Sensing and Geographical Information System (GIS) to find the rate the trend, location, and land cover replacement of deforestation in Central Kalimantan Province, Indonesia. The research found that during the period Central Kalimantan lost 1.5 million ha of natural forest with the rate of deforestation 117,000 ha/year. In general, the deforestation shown decrease trend and fluctuated during the period. Deforestation majority takes place at secondary swamp and dry forest that are located at south part of the island. Most of deforestation resulted shrubs, plantations, and agriculture land. The finding of this research could be used as a base to determine the target location for rehabilitation strategy and approach to prevent further deforestation.

Landslide is one of the most common geological disasters in China, which is characterized by suddenness and uncertainty, and it is difficult to realize accurate identification, early warning and forecasting of landslide disaster by conventional means. With the development of high-resolution remote sensing satellites and InSAR surface deformation monitoring technology, the traditional means of landslide monitoring data sources are limited, and there is a lack of effective methods to excavate the characteristics of the spatial distribution of landslide hazards and their triggering factors and other issues. In this paper, the area extending 10 km outside the VII isobar of the Gengma earthquake is taken as the study area, and 13 evaluation factors are screened out by integrating the factors of InSAR surface deformation, topography and geological environment, and the Bayesian Optimized Convolutional Neural Network (BO-CNN) is used for the evaluation of landslide susceptibility, and the BO-RF and PSO-SVM models are selected for the comparative analysis. The model accuracy evaluation was carried out by three indexes: ROC curve, AUC value and FR value, in which the ROC curves of PSO-SVM, BO-RF and BO-CNN were all close to the upper-left corner of the corner, and the AUC values were 0.9388, 0.9529, and 0.9535, respectively, and the FR value of landslide in the high susceptibility area of BO-CNN was as high as 14.9, and was higher than that of PSO-SVM and BO-RF, respectively. SVM and BO-RF model is 4.55 and 3.69 higher, the experimental results show that the BO-CNN model used in this paper has a better effect in landslide susceptibility evaluation, and the research results of the local government's disaster prevention and mitigation measures are of great significance.

Various studies on the physical characteristics of the canopy gaps in tropical and subtropical regions but that in the mangrove swamp forest in Malaysia is little known. The objectives of this study are to assess the canopy gaps physical characteristics (size, form, direction), to assess the changes in soil physical characteristics and microenvionment in and around the canopy gaps. Five canopy gaps were selected formed by lightning strikes, gaps size and shapes were determined using the portable Global Positioning System and photographic images were analysed using ForestCrown. Result shows that canopy gap opening has increased the total light reaching the forest floor, changed the canopy gap microenvironment. Strong correlation between canopy opening percentage and temperature of gaps explains the changes of canopy gaps characteristics. These changes have contributed to new seedling germination, regeneration and maintaining the canopy gap dynamics.

In recent years, how to combine intelligent prospecting algorithms such as random forest with a large number of geological and mineral data for quantitative prediction of exploration geochemistry has become an important topic of concern to quantitatively improve the accuracy of target delineation. The ore-forming geological conditions in the central Kunlun area of Xinjiang are great and have good prospecting prospects. However, due to the exhaustion of shallow deposits and the lag of geological prospecting work in the past ten years, there has been no expected breakthrough in the search for large and super-large metal deposits for many years. There has been a serious shortage of reserve resources. The use of new theories, new methods and new technologies for mineral resources investigation and evaluation has become an urgent need in the current prospecting work. In view of this, based on the existing spatial database of geological and mineral resources in the central Kunlun of Xinjiang, combined with the geological characteristics, genesis and metallogenic regularity of the area, this paper carried out a series of studies on gold polymetallic minerals with the help of geographic information system and data science programming software platform. The researchers integrated geological and regional geochemical data, and constructed a random forest metallogenic discriminant model based on two different sampling methods (integrated random undersampling and selection of training samples) to predict the mineralization of gold polymetallic minerals in the central Kunlun area of Xinjiang and delineate the metallogenic target area. The quantitative prediction of gold polymetallic mineral resources in the central Kunlun area of Xinjiang by two random forest models is compared and discussed: the known ore spots, fault structures and geochemical information are extracted, and the known gold polymetallic ore spots and geochemical data are used to form a training set and a prediction set to construct a machine learning random forest model. The results of prediction evaluation and metallogenic prospect division show that for different sampling methods, the performance evaluation parameters of the training process show that the prediction accuracy of the selected training samples is higher, and the selected training samples are more reliable because they can fully learn the complex information of the original data. In the metallogenic prospect prediction and metallogenic potential division, the random forest model of selecting training samples has more reference value and further exploration research significance in the production problem considering the actual exploration cost because of its small area of high potential prediction area and high proportion of ore bearing per unit area. At the same time, this study innovatively improves the prediction accuracy, reduces the exploration risk, and expands the prospecting idea of machine learning algorithm in mathematical geology in the central Kunlun area of Xinjiang. The delineated metallogenic potential area has positive guiding significance for the actual gold polymetallic prospecting work in this area.

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

In healthy humans, taste sensitivity varies widely, influencing food selection and nutritional status. Chemosensory reductions have been associated with numerous pathological disorders or pharmacological interventions. Reliable psychophysical methods are crucial resources to analyze the taste function during routine clinical assessment. However, in the daily clinical routine, they are often considered to be too time-consuming. We used the Supervised Learning (SL) regression method to analyze with high precision the overall taste status of healthy controls (HC) and patients with chemosensory loss and to characterize the combination of responses that best can predict the overall taste status of two groups. Random Forest regressor allowed us to achieve our objective. The analysis of the order of importance and impact of each parameter on the prediction of overall taste status in the two groups showed that salty (low concentration) and sour (high concentration) stimuli specifically characterized healthy subjects, while bitter (high concentration) and astringent (high concentration) stimuli identified patients with chemosensory loss. The identification of these distinctions appears to be of interest to the health system since they may allow the use of specific stimuli during routine clinical assessments of taste function reducing the commitment in terms of time and costs.

The response of boreal vegetation to global warming has shown a weakening trend over the last three decades. However, in previous studies, models of vegetation activity responses to temperature change have often only considered changes in mean daily temperature (Tmean), with the diurnal temperature range (DTR) being neglected. The goal of this study is to evaluate the temporal trends of the relationships between two temperature factors (Tmean and DTR) and vegetation activity across the boreal regions on both annual and seasonal timescales, by simultaneously employing satellite and climate datasets. We found that the interannual partial correlation between growing season (GS) NDVI and Tmean (RNDVI−Tmean) showed a significant decreasing trend over the last 34 years. At the seasonal scale, RNDVI−Tmean shows a significant upward trend in the spring, while in the summer and autumn, RNDVI−Tmean exhibits a significant downward trend. The temporal trend characteristics of the partial correlation between NDVI and DTR (RNDVI−DTR), at both the GS and seasonal scales, are fully consistent with RNDVI−Tmean. The area with a significant decrease in GS RNDVI−Tmean and RNDVI−DTR accounted for approximately 44.40% and 41.21% of the boreal region with the 17-year moving window, respectively. In stark contrast, the area exhibiting a significant increasing trend in GS RNDVI−Tmean and RNDVI−DTR accounted for only approximately 14.65% and 13.59% of the boreal region with the 17-year moving window, respectively. With respect to the seasonal patterns of RNDVI−Tmean and RNDVI−DTR, the area with a significant upward trend in spring was greater than that with a significant downward trend. Nevertheless, more areas had a significant downward trend of RNDVI−Tmean and RNDVI−DTR in summer and autumn than had a significant upward trend. Overall, our research reveals a weakening trend in the impact of temperature on vegetation activity in the boreal regions, and contributes to a deeper understanding of the vegetation response to global warming.

Forest vegetation dynamics (succession and dominance) is an ecological phenomenon that is still difficult to characterize and integrate into management practices. In this study, the understanding of forest dynamics is explored based on Grime’s theoretical triangular model of plant adaptive strategies using the example of Lithuania’s forest ecosystems. The idea behind this is the hypothesis that forest dynamics is linked to natural selection as an evolutionary process that exhibits differential species responses to competition, stress, and disturbance. The aim of this study is to explore the adaptive relationships in hemi-boreal forests. Grime’s and Pierce’s secondary CSR strategies, which describe various equilibria between competitiveness (C), stress tolerance (S), and ruderalism (R), were considered to reflect four establishment and development adaptive specialization characteristics of forest tree species. As a result of the study, four types of tree functional groups were identified: stress-resistant ruderals, competitive stress-sensitive ruderals, ruderal stress-sensitive competitors, and stress-resistant competitors. Based on this, we propose that reforestation move away from single species regeneration by implementing the maintenance of these four types of functional groups. In conclusion, forest management must consider the existence of the established equilibria between plant competitiveness, stress tolerance, and ruderalism. The formal concepts presented in this article can serve as a guide for future relevant research and development of appropriate methods for studying real forests. This study is unique in that no previous work has linked forest dynamics and natural selection in the context of Lithuania’s forest ecosystems.