Search Results (146)

Silvopastoral systems in Patagonia (Argentina) aim to synergize forest and grassland productivity through thinning interventions in native forests of Antarctic beech (Nothofagus antarctica (G.Forst.) Oerst.), locally known as ñire, modifying ecosystem dynamics. This study aimed to determine how thinning strategies modify microclimatic conditions (air and soil temperatures, precipitation, soil water content) and modulate the intra-annual radial growth patterns in N. antarctica trees within subpolar deciduous forests of Tierra del Fuego, Argentina. We established three treatments: unmanaged mature forest (UF), thinning under crown cover influence (UC), and thinning outside crown cover influence (OC). Microclimate and radial growth were continuously monitored using high-precision dendrometers and associated data loggers during the 2021–2022 and 2023–2024 growing seasons. Data were analyzed using Generalized Linear Mixed Models and Principal Component Analysis. OC treatment consistently exhibited the highest total annual radial growth, averaging 1.44 mm yr⁻¹, which was substantially greater than the observed in both the UC (0.56 mm yr⁻¹) and UF (0.83 mm yr⁻¹) across the two seasons. An advanced growth dynamic, with cambial activity starting approximately five days earlier than in UF and UC, was detected. Air temperature was a primary positive driver of daily growth (GLMM Estimates > 0.029, p < 0.001 for all treatments), while soil water content (SWC) was significantly higher in OC (mean 25.4%) compared to UF (22.3%) and UC (15.9%). These findings showed that OC, characterized by higher soil moisture, likely facilitated the trees’ ability to capitalize on warm temperature days. This accelerates and extends the period of radial growth, offering a direct strategy to enhance productivity in these silvopastoral systems, essential for long-term forest sustainability. Full article

Climate change, driven largely by anthropogenic greenhouse gas emissions, is a major global issue. Long-term high-frequency measurements of gas fluxes remain limited, especially outside the growing season. This study addresses two key gaps: the absence of continuous annual data capturing diurnal and seasonal variations, and the biases from suboptimal sampling timing. Using automated chambers, we monitored soil CO₂ and CH₄ fluxes throughout 2016 in a temperate forest on Changbai Mountain, China. Our results showed a strong negative correlation between annual CO₂ and CH₄ fluxes, with a slope of −0.21 and R² of 0.70. This relationship persisted from March to November but was absent during the winter and April. Both gases exhibited the largest diurnal variations in summer. Statistical analysis identified 16:00 as the optimal single sampling time for estimating daily mean fluxes in most months. CO₂ fluxes were primarily governed by temperature but modulated by VWC (soil volumetric water content). They were suppressed during summer drought and enhanced during winter freeze–thaw cycles. CH₄ uptake rates were strongly dependent on VWC throughout the growing season, while their temperature response underwent a reversal from positive in summer to negative in winter. Decision tree analysis revealed nonlinear threshold responses. CO₂ fluxes exhibited three temperature thresholds between 5.30 and 15.64 °C and two VWC thresholds between 0.30 and 0.42 m³ m⁻³. CH₄ fluxes showed five temperature thresholds ranging from 2.34 to 15.71 °C and seven VWC thresholds from 0.11 to 0.44 m³ m⁻³. The strongest anticorrelation between CH₄ flux and temperature occurred at intermediate VWC levels. This study provides detailed characteristics of greenhouse gas fluxes based on complete annual high-frequency data. It emphasizes the importance of year-round monitoring and offers improved sampling strategies and mechanistic insights for better flux monitoring and climate prediction. Full article

In the retail industry, demand forecasting is absolutely crucial for guaranteeing efficient inventory and supply chain control. Different artificial intelligence (AI) techniques have been used lately to improve forecasting performance. Demand fluctuation, seasonal patterns, and outside influences continue to create difficulties, though. Using several machine-learning techniques Linear Regression, XGBoost, Random Forest, Decision Tree, Prophet, and LSTM this paper offers a comparative study to forecast product demand. A retail dataset obtained from Kaggle served as the basis for training and testing the forecasting models. The experimental results demonstrate that the LSTM model outperforms all others with accuracy, precision, recall, and F1-score of 92.31%, 92.31%, 100.00%, and 96.00%, respectively, followed by Prophet with 85.71%, 92.31%, 92.31%, and 92.31%, respectively, Decision Tree with 93.05%, 75.76%, 76.13%, and 75.94%, respectively, Random Forest with 91.99%, 66.86%, 88.08%, and 76.02%, respectively, XGBoost with 83.21%, 45.70%, 87.84%, and 60.12%, respectively, and Linear Regression with 60.67%, 25.46%, 89.75%, and 39.67%, respectively. These results verify that ensemble and deep learning models can greatly help retailers in raising operational efficiency and notably improve forecasting accuracy. Full article

Desert regions face unique challenges under climate change, including the emerging phenomenon of sand dune expansion. This research investigates aeolian sand transport in the Seqale watershed (eastern Iran) using geostatistical and machine learning methods to model and forecast dune spread, aiming to reduce the loss of sustainability in these valuable landscapes. Predictor variables (altitude, slope, climate, land use, etc.) and wind erosion occurrence were analyzed using classification algorithms (decision tree, random forest, etc.) and bivariate methods (information value, area density) in R software 4.5.0. Risk zoning maps were created and evaluated by combining these approaches. Results indicate a higher sand dune presence in regions with specific altitude (1200–1400 m), gentle northeast-facing slopes (2–5 degrees), moderate rainfall (250–500 mm), high evaporation (2500–3000 mm), outside flood plains, and far from roads (>3000 m) and water channels (>500 m). Dune expansion maps based on density area and information value methods showed substantial areas classified as high to very high movement risk. Machine learning analysis identified the Support Vector Machine (SVM) algorithm (AUC = 0.94) as the most effective for classifying sand dune zones. The study concludes that spatial forecasts, combined with tailored physical and biological measures, are essential for effective sand dune management in the region. Full article

Typically, dimension stones, commonly called stone blocks, are cut into multiple small cuboid stones so that multiple sculptures can be produced. To use the stone block as efficiently as possible, it is essential to pack these small cuboids in each stone block as efficiently as possible while satisfying the limitations of the machining. This paper describes methods for packing and cutting stone blocks using nonlinear programming that generate sets of trees, which are also called forests, that decide the packing layout of the small cuboids inside the block. The containers and elements have their own prices and values, respectively. The elements can be translated to the corners of the containers or to the corners of the elements that are already in the containers, if the elements are not outside the containers after the translation. Then, the problem can be interpreted as finding the best forest that packs the elements as efficiently as possible at the lowest total price of containers, which is a subset of all containers. The formula for the score that defines the compactness of the packing is in this paper. The user can define the number of forests so that parallel computing methods can be applied. Each forest is generated randomly. Two different packing methods are introduced: simple packing and slab packing. Simple packing is based on a non-guillotine cutting method and slab packing is a guillotine cutting method for realistic scenarios, such as scenarios with machining limitations. By using this method, it is possible to plan the cutting in a digital environment, which is not possible when using the traditional method with physical templates. Furthermore, by restricting the rotation of the elements, it is possible to make the elements follow the horizontal vein direction of the stone blocks, which is a common vein direction in travertine. Full article

Peptide therapeutics often fall outside classical small-molecule heuristics, such as Lipinski’s Rule of Five (Ro5), motivating the development of adapted filters and data-driven approaches to early drug-likeness assessment. We curated >300 k drug (small and peptide) and non-drug molecules from PubChem, extracted key molecular descriptors with RDKit, and generated three rule-violation counters for Ro5, the peptide-oriented beyond-Ro5 (bRo5) extension, and Muegge’s criteria. Random Forest (RF) classifier and regressor models (with 10, 20, and 30 trees) were trained and evaluated. Predictions for 26 peptide test molecules were compared with those from SwissADME, Molinspiration, and manual calculations. Model metrics were uniformly high (Ro5 accuracy/precision/recall = 1.0; Muegge ≈ 0.99), indicating effective learning. Ro5 violation counts matched reference values for 23/26 peptides; the remaining cases differed by +1 violation, reflecting larger structures and platform limits. bRo5 predictions showed near-complete agreement with manual values; minor discrepancies occurred in isolated peptides. Muegge’s predictions were internally consistent but tended to underestimate SwissADME by ~1 violation in several molecules. Four peptides (ML13–16) satisfied bRo5 boundaries; three also fully met Ro5. RF models thus provide fast and reliable in silico filters for peptide drug-likeness and can support the prioritisation of orally developable candidates. Full article

Although treeline ecotones are significant components of vulnerable mountain ecosystems and key indicators of climate change, treelines of the Southern Hemisphere remain largely outside of research focus. In this study, we investigate, for the first time, the current and future distribution of the treeline species Nothofagus pumilio in the Southern Andes using a Species Distribution Modelling approach. The lack of modelling studies in this region can be contributed to missing occurrence data for the species. In a preliminary study, both point and raster data were generated using a novel Instagram ground truthing approach and remote sensing. Here we tested the performance of the two datasets: a typical binary species dataset consisting of occurrence points and pseudo-absence points and a continuous dataset where species occurrence was determined by supervised classification. We used a Random Forest (RF) classification and a RF regression approach. RF is applicable for both datasets, has a very good performance, handles multicollinearity and remains largely interpretable. We used bioclimatic variables from CHELSA as predictors. The two models differ in terms of variable importance and spatial prediction. While a temperature variable is the most important variable in the RF classification, the RF regression model was mainly modelled by precipitation variables. Heat deficiency is the most important limiting factor for tree growth at treelines. It is evident, however, that water availability and drought stress will play an increasingly important role for the future competitiveness of treeline species and their distribution. Modelling with binary presence–absence point data in the RF classification model led to an overprediction of the potential distribution of the species in summit regions and in glacier areas, while the RF regression model, trained with continuous raster data, led to a spatial prediction with small-scale details. The time-consuming and costly acquisition of complex species information should be accepted in order to provide better predictions and insights into the potential current and future distribution of a species. Full article

Oak–lime–hornbeam forests are among the most biodiverse temperate forests. This study compared older managed stands with a strictly protected old-growth forest in terms of their features. Managed forests at various stages of silvicultural operations were selected: a mature stand where regeneration cuts had not yet begun, as well as stands where such treatments were in the initial or advanced stages. Stand features that may affect the diversity and density of avifauna were analyzed on the basis of 151 sample plots. In four successive breeding seasons, birds in these stands were surveyed. The stands differed significantly in volume, the density of large trees, regeneration, the vertical structure, and the amount of deadwood. The number of bird species was the highest in the initial and advanced gap-cut stands. Group-selection cutting in those stands led to a succession of non-forest bird species and, hence, a greater number of birds building nests on or close to ground as compared to the old-growth forest. The old-growth forest was the most similar to the mature managed stand in terms of bird species composition (Jaccard index = 0.76). The old-growth forest was characterized by the highest bird density (91 pairs per 10 ha), with more than half of the breeding pairs being cavity nesters. In the managed forest, the bird density was from 63 to 72 pairs per 10 ha. Based on the present study, it can be concluded that effective conservation of bird assemblages is possible in managed forests, provided that certain concessions are made. Drawing on the characteristics of old-growth forests, several guidelines can be proposed for forest management. First and foremost, it is essential to maintain a mosaic forest structure. Secondly, it is necessary to retain an adequate number of large, old trees within the stand and to ensure a sufficient volume and diversity of deadwood. Additionally, it is absolutely critical to shift timber harvesting activities outside of the bird breeding season. Full article

Land managers across the United States (U.S.) are developing plans to mitigate climate change. Effective implementation and monitoring of these climate action plans require standardized methods and timely, accurate geospatial data at appropriate resolutions. Despite the abundance of geospatial and statistical data in the U.S., a significant gap remains in translating these data into actionable insights. To address this gap, we developed the Land Emissions and Removals Navigator (LEARN), an online tool that automates subnational greenhouse gas (GHG) inventories of forests and trees in nonforest lands using a standardized analytical framework consistent with national and international guidelines. LEARN integrates multiple datasets to calculate land cover and tree canopy changes, delineate areas of forest disturbance, and estimate carbon emissions and removals. To demonstrate the application of LEARN, this paper presents case studies in Jefferson County, Washington; Montgomery County, Maryland; and federally owned forests across the conterminous U.S. Our results highlight LEARN’s capacity to provide localized insights into carbon dynamics, enabling subnational entities to develop tailored climate strategies. By enhancing accessibility to standardized data, LEARN empowers community land managers to more effectively mitigate climate change. Future developments aim to expand LEARN’s scope to cover nonforest landscapes and incorporate additional decision-making functionalities. Full article

Accelerating the recovery of compacted soils caused by logging machinery using bioengineering techniques is a key goal of Sustainable Forest Management. This research was conducted on an abandoned skid trail with a uniform 15% slope and a history of heavy traffic, located in the Nav forest compartment of northern Iran. The main objectives were to assess (a) soil physical properties 35 years after skidding by a tracked bulldozer, (b) the impact of natural alder regeneration on soil recovery, and (c) the contribution of alder fine-root development to the restoration of compacted soils in beech stands. Soil physical properties and fine root biomass were analyzed across three depth classes (0–10 cm, 10–20 cm, 20–30 cm) and five locations (left wheel track (LT), between wheel tracks (BT), right wheel track (RT)) all with alder trees, and additionally control points inside the trail without alder trees (CPWA), as well as outside control points with alder trees (CPA). Sampling points near alder trees (RT, LT, BT) were compared to CPWA and CPA. CPA had the lowest soil bulk density, followed by LT, BT, RT, and CPWA. Bulk density was highest (1.35 ± 0.07 g cm⁻³) at the 0–10 cm depth and lowest (1.08 ± 0.4 g cm⁻³) at 20–30 cm. The fine root biomass at 0–10 cm depth (0.23 ± 0.21 g dm⁻³) was significantly higher than at deeper levels. Skid trail sampling points showed higher fine root biomass than CPWA but lower than CPA, by several orders of magnitude. Alder tree growth significantly reduced soil bulk density, aiding soil recovery in the study area. However, achieving optimal conditions will require additional time. Full article

The Miombo woodlands are declining in both area and value, primarily due to over-harvesting of commonly preferred species. These forests, however, still contain several other species that are potentially of commercial importance. This study aimed to address the need for improved volume and biomass estimates for the sustainable management and utilization of two of the most abundant timber species in Mozambique’s Miombo woodlands: Brachystegia spiciformis (common name: Messassa) and Julbernardia globiflora (common name: red Messassa). Non-linear models were developed to estimate the merchantable wood volume under bark, heartwood volume, and biomass. The volume and biomass models for wood and heartwood volume, which included both diameter at breast height (DBH) and tree height as predictor variables, outperformed single-predictor models. However, the performance of some ratio models using DBH as the only predictor variable surpassed that of models using two predictor variables. The developed models are recommended for adoption by forest companies to increase economic and environmental benefits as they can refine harvest planning by improving the selection of trees for harvesting. Proper tree selection enhances the rate of recovery of high-quality timber from heartwood while observing sustainable forest management practices in Miombo and increasing the proportion of carbon removed from forests, which is subsequently stored in wood products outside the forest. Full article

Soil pollution at airports is a critical environmental issue that affects not only the local ecology but also the health of people living near these infrastructures. The main causes of pollution include the use of chemical products such as de-icing agents, fuels, and lubricants, as well as waste from aircraft and ground vehicles. These substances often seep into the soil, leading to the accumulation of toxic elements. However, due to security reasons, there is a great scarcity of real data on the impact of airport operations on ecosystems and the role trees could play in pollutant limitation. Thus, the aim of this study was to determine whether airport operations have toxic effects on soils within and around Macedonia Airport, Thessaloniki, Northern Greece, by determining the concentrations of potentially toxic elements (Cu, Ni, Pb, Mn, Fe, Co, Cr, Cd, and Zn) in soil samples taken within the airport and near the airport. Furthermore, this study aimed to investigate the effect of the canopies of forest species on the accumulation of toxic metals in the soil inside the airport and in the peripheral zone. The results show that, overall, no important pollution was detected in the soil of the Thessaloniki Airport, Northern Greece, both inside and outside the airport area. Some differences were observed in the content of toxic metals studied between the samples taken inside and outside the airport, and some effects of tree canopy were noted. However, all values were lower than the defined permissible limits according to international standards (except for iron). It is important, however, to perform regular re-checking of soil quality with new samples in order to prevent soil contamination and mitigate any contamination found. Full article

The stem taper function is essential in predicting diameter outside bark (DOB) variations along the tree height, contributing to volume estimation, harvest planning, and precision forestry. Traditional taper models, such as the Kozak function, offer interpretability but often fail to capture nonlinear growth dynamics and regional variability, particularly in the upper stem segments. This study aimed to evaluate and compare the prediction accuracy of conventional and machine learning-based taper models using Pinus densiflora, a representative conifer species in Korea. Field data from two ecologically distinct regions (Gangwon and Central Korea) were used to build and test four models: the Kozak taper function, random forest, extreme gradient boosting, and an artificial neural network (ANN). Model performance was assessed using the RMSE, R², and MAE, along with stem profile visualizations for representative trees. The results showed that the ANN consistently achieved the highest prediction accuracy across both regions, particularly at an upper crown zone relative height (RH) > 0.8, while maintaining smooth and stable taper curves. In contrast, the Kozak model tended to underestimate the diameter of the upper stem. This study demonstrates that machine learning models, particularly ANNs, can effectively enhance the taper prediction precision and serve as practical tools for data-driven forest management and the implementation of precision forestry in Korea. Full article

Winch-assisted harvesting has expanded considerably in recent years as it enables ground-based machines to work safely on steep slopes. To analyze operator exposure to whole-body and hand–arm vibration (WBV, HAV) and noise exposure (LA_eq, LC_peak) during winch-assisted harvesting (TW) and harvesting without winch assistance (NTW), a field study using a Ponsse Scorpion King harvester and an Ecoforst T-winch traction winch was conducted. Vibrations were measured at three locations inside the cabin (seat, seat base/floor, control lever), while noise exposure was recorded both inside and outside the cabin. WBV exposure during work time operations was highest in the Y-direction, both on the seat (0.49–0.87 m/s²) and on the floor (0.41–0.84 m/s²). The WBV and HAV exposure levels were highest while driving on the forest and skid road. Exposure during the main productive time was significantly influenced by the harvesting system, diameter at breast height (DBH), and tree species. Noise exposure was higher, while WBV and HAV exposures on the seat, floor and control lever were lower during non-work time than during work time. The daily vibration exposure on the seat exceeded the EU action value, while LC_peak noise exposure surpassed the limit value of 140 dB(C) on all measured days. Noise and vibration exposure were constantly higher during TW than NTW harvesting but differences were small. Compared to other studies, the results show that harvesting on steep terrain increases noise and vibration exposure, while non-work time has the opposite effect on vibration and noise exposure. Full article

This study aimed to evaluate the role of trees outside forests on agricultural land (TOF-AL) in preserving the initial aboveground biomass (AGB) of forests within the agricultural landscape of Mongala province in the Democratic Republic of Congo. In 2024, tree inventories were conducted over four months in the forests and agricultural lands of Mongala province to analyse AGB. The effects of artisanal logging and charcoal production activities on the AGB conservation rate were considered. This study indicates that 78.3% of the trees encountered in agricultural lands were large-diameter trees (diameter at breast height (DBH) ≥ 60 cm). In forest areas, large-diameter trees accounted for 55.9% of tree density. The average AGBs are 66.8 Mg ha⁻¹ for TOF-AL and 373.5 Mg ha⁻¹ for forest trees. The AGB of TOF-AL accounts for 17.9% of the AGB of the total forest trees. The AGB conservation rates vary by region, with Lisala having the highest at 22.1%, Bumba the lowest at 11.2%, and Bongandanga at 20.5%. Artisanal logging and charcoal production reduce the AGB conservation rate of TOF-AL. The AGB conservation rate is positively correlated with the distances to major cities. These results prove that conserving trees in agricultural landscapes can reduce the AGB losses associated with slash-and-burn agriculture and contribute to mitigating climate change effects. Full article