Search Results (12,557)

Reliable short-term agroclimatic forecasting is essential for precision agriculture, irrigation planning, disease-risk assessment, and microclimatic decision support. However, field-deployed sensor systems often operate under degraded data conditions, including missing measurements, noise, temporal interruptions, and limited local computational resources. These constraints make it necessary to evaluate not only forecasting accuracy under clean data, but also model robustness under realistic sensor-data degradation. The objective of this study is to compare machine-learning models for one-step-ahead agroclimatic time-series forecasting under degraded sensor-data conditions. Using a real meteorological dataset collected by a field weather station in the Dnipro region of Ukraine, twelve regression models were evaluated: Ridge Regression, Random Forest, Extra Trees, Gradient Boosting, HistGradientBoosting, Support Vector Regression, Linear SVR, KNN, PLSRegression, ElasticNet, Lasso, and MultiTaskElasticNet. The models were tested under five controlled scenarios: baseline data, missing values, additive noise, reduced training history, and combined noise–missingness degradation. Quantitatively, Ridge Regression achieved the strongest baseline temperature-forecasting performance, with MAE = 0.318 and R² ≈ 0.98 under clean data. It also maintained R² > 0.90 when trained on only 50% of the available history. Under Gaussian noise with σ = 0.05–0.10, Ridge Regression and HistGradientBoosting maintained R² values in the range of 0.95–0.97, whereas under combined degradation with σ = 0.10 and 20% missing data, HistGradientBoosting retained R² > 0.85. These findings indicate that machine-learning models differ substantially in their sensitivity to sensor-data degradation and that robustness-oriented benchmarking is necessary before selecting models for agroclimatic forecasting systems. Full article

Walnut leaf necrosis causes leaf desiccation and premature abscission, substantially reducing photosynthetic efficiency, impairing fruit development, and ultimately leading to yield loss and quality deterioration. In severe cases, it accelerates branch senescence or even whole-tree mortality, resulting in considerable economic damage to the walnut industry. Rapid and accurate monitoring of this disease is therefore essential for sustainable production. This study aimed to characterize the different stages of walnut leaf necrosis using spectral analysis and develop classification models for stage-specific identification. Leaf samples representing healthy leaves and the early, middle, and late stages of necrosis were analyzed for spectral responses. Sensitive bands were identified using the variable importance in projection (VIP), successive projections algorithm (SPA), and the combined VIP-SPA method, and corresponding vegetation indices were constructed. The selected features were incorporated into classification models based on random forest (RF), extreme gradient boosting (XGBoost), and convolutional neural networks (CNNs). Results revealed that the red-edge (640–700 nm) and near-infrared (720–1000 nm) regions were identified as key diagnostic spectral ranges. Among the vegetation indices evaluated, the Simple Ratio Index (SRI) calculated from reflectance at 705.7 nm and 707.1 nm, the Normalized Difference Index (NDI) using the same band pair, and the Difference Index (DI) derived from 417.1 nm and 638.7 nm emerged as the most sensitive indicators of disease severity. Classification accuracies for different necrosis stages reached 0.9583, 0.9583, and 0.9333, respectively. These findings demonstrate that the identified spectral bands and vegetation indices provide robust tools for monitoring the progression of walnut leaf necrosis. Full article

Despite the growing relevance of governance and sustainability in port management, there is still limited empirical evidence on how economic, social, and environmental dimensions interact in a non-linear and configurational manner to explain port economic efficiency. This study applies an explainable machine learning approach based on Random Forest to classify the economic efficiency of Spanish Port Authorities using an integrated set of governance-related indicators. Economic efficiency is approximated through the E_02 indicator (EBITDA per tonne), which is discretized into three ordinal levels: low, medium, and high efficiency. A classification approach is preferred over regression because the objective is not only to predict a continuous value, but to identify interpretable efficiency profiles and extract decision rules associated with different governance configurations. Model performance was evaluated using a confusion matrix, global accuracy, precision, recall, and F1-score for each efficiency class. The results reveal three differentiated patterns: low-efficiency ports, associated with environmental weaknesses, fragile labor structures, and low profitability; medium-efficiency ports, characterized by partial strategies and transitional configurations; and high-efficiency ports, linked to coherent combinations of environmental management, balanced labor organization, and strong economic performance. Overall, the findings show that port efficiency does not depend solely on size or isolated factors, but on specific governance-related configurations. The study highlights the value of explainable artificial intelligence as a complementary tool to support evidence-based decision-making in sustainable port management. Full article

The integration of quadruped robotics with advanced sensing technologies offers a transformative approach to forest management, particularly for real-time measurement of tree Diameter at Breast Height (DBH). This paper introduces a novel methodology by deploying a quadruped robot equipped with GPS, LiDAR, and an aligned high-definition camera to patrol forest paths via a developed dynamic autonomous mission. Utilizing a YOLO-based model for trunk detection, the methodology retrieves precise DBH measurements and corresponding geotags, constructing a spatial database of DBH ground-truth data. This database serves as a real-time ground-truth lookup table to calibrate allometric equations used in drone-based crown detection missions, enhancing the accuracy of forest biophysical attribute estimations such as tree height, volume, and biomass. Experimental validation demonstrates high precision in DBH estimation (error < 5% in controlled tests), supporting automated, around-the-clock data collection for sustainable forest management in Mediterranean ecosystems. Full article

Understanding how P availability affects root turnover and P redistribution within plants is essential for optimizing fertilization strategies and sustaining forest growth under low-P soils. This study evaluated the effects of P fertilization on root system dynamics, plant growth, and P nutrition of Handroanthus heptaphyllus, a flowering landscape tree, cultivated in a subtropical climate. Plants were grown under two soil P levels (low and high). Plant height, stem diameter, leaf P concentration, soil P availability, total numbers of living and dead fine roots, total fine root surface area, and fine root production rate were measured at 18, 24, 30, and 36 months after planting. Phosphate fertilization increased soil P availability during the first 24 months and resulted in significant gains in plant height, stem diameter, fine root production, total surface area, and the ratio between living and dead fine roots, indicating a higher proportion of living roots relative to dead ones. Under high P availability, the greatest fine root production and surface area of living fine roots occurred in the 0–20 cm soil layer, reflecting localized P application near the plants. High P availability enhanced root system development, promoted greater soil exploration, and improved P uptake. These results indicate that under P supplementation, plants strategically invest in root growth, improving nutrient acquisition efficiency and reducing dependence on external inputs. Increased phosphorus availability enhances root growth and increases fine root production and turnover. Minirhizotron monitoring effectively captured shifts in root system dynamics driven by P availability, including enhanced root growth, increased fine root production and turnover, and improved nutrient uptake under high P, as well as limited root activity under low P conditions, indicating a more conservative strategy with reduced investment in root production. Full article

Unattended scheduled appointments (“patient no-shows” henceforth) adversely affect healthcare providers and patients’ health, disrupting the continuity of care, operational efficiency, and allocation of medical resources. Therefore, accurate predictive modeling is needed to reduce the impact of patient no-shows. Although machine learning methods, such as logistic regression, random forests, and decision trees, are widely used to predict patient no-shows, they often rely on hard decision splits and static feature importance, limiting adaptability to complex patient behaviors. To address this limitation, we propose a hybrid multi-head attention soft random forest (MHASRF) model that integrates attention mechanisms into a random forest using probabilistic soft splitting. It assigns attention weights across the trees, enabling attention on specific patient behaviors. The MHASRF model exhibited an accuracy of 88.24%, specificity of 91.21%, precision of 81.60%, recall of 82.01%, F₁-score of 81.81%, and area under the receiver operating characteristic curve of 94.07%, demonstrating high and balanced performance across metrics. It could also identify key predictors of patient no-shows at two feature-importance levels (tree and attention mechanism), providing deeper insights into patient no-shows. Thus, the proposed MHASRF model is a robust, adaptable, and interpretable method for predicting patient no-shows that can help healthcare providers optimize resources. Full article

Accurate estimation of tree Above-Ground Biomass (AGB) is critical for the timely monitoring of forest dynamics. However, the scarcity of high-quality in situ measured data introduces considerable uncertainty into the precise spatial mapping of AGB. In this study, a novel method for AGB mapping is proposed to enhance the accuracy of AGB estimation based on the Semi-Supervised Ensemble Learning (SSEL) strategy. By expanding the sample set via an iterative self-training approach based on an Inverted Query-by-Committee (I-QBC) strategy, the model significantly enhances the accuracy of AGB estimation. Using Sentinel-2 data, the experimental results show that: (1) The I-QBC-driven SSEL model demonstrated significantly higher estimation accuracy for AGB compared to conventional tree-based ensemble models. Optimal stability (${\mathrm{R}}^2$ = 0.80) and peak accuracy (${\mathrm{R}}^2$ = 0.88) were achieved at sample increments of 20 and 30, respectively. (2) Among various feature types, Recursive Feature Elimination with Cross-Validation (RFECV) identified GNDVI, PSSRa, slope and texture correlation as the most critical predictors for AGB estimation in the study area. (3) The total AGB stock in the study area is estimated to range from 1.46 × 10⁷ Mg to 1.71 × 10⁷ Mg. The SSEL model provides a valuable reference for AGB estimation under sparse ground-truth sample conditions, while offering a novel approach for large-scale AGB mapping. Full article

This study presents the results of a classification of the types of water supply pipe failures using a random forest model consisting of 72 trees. The modeling was done in Statistica software. The classification accuracy was compared with earlier results obtained from single-classification-tree models. The qualitative-dependent variable was the type of failure (corrosion, crack, sealing). The predictors included quantitative variables (diameter, year of construction) as well as qualitative variables (pipe type and material). The choice of 72 trees was made based on an analysis of the misclassification rate (31%) during the training stage. Increasing the number of trees forming the forest did not produce more accurate classification results: for the test set, the accuracy was 82%, 72%, and 37% for corrosion, crack, and sealing failures, respectively. The trees forming the random forest differed in their structure both in terms of the number of split and terminal nodes, as well as in the depth and number of levels of individual trees. The overall classification accuracy for the test set was nearly 66%, which is a better result than in the earlier analyses based on single trees. The proposed approach also aligns with the currently promoted concept of the sustainable operation of critical infrastructure. Full article

In the assessment of bearing capacity for in-service bridge pile foundations, static load tests are costly, destructive, and difficult to scale. The traditional dynamic formula approach relies heavily on an empirical dynamic–static conversion coefficient that introduces considerable uncertainty. To address these limitations, this study proposes a non-destructive evaluation method for pile foundation bearing capacity based on measured dynamic stiffness and machine learning algorithms. Using data from a highway bridge inspection project, a dataset comprising 680 piles was compiled, including measured dynamic stiffness, geometric parameters, and design load information. An end-to-end binary classification model was constructed to map multidimensional physical features to an engineering decision target, namely, whether the bearing capacity meets the design requirement. The performance of several algorithms was compared, including logistic regression, random forest, and gradient boosting decision tree (GBDT). Among the evaluated models, the GBDT model demonstrated the best capability for capturing the complex nonlinear pile–soil interactions. On an independent test set, it achieved an accuracy of 96.3% and an F1 score of 0.96, with a very low false-negative rate, satisfying the high precision required for engineering safety screening. Feature importance analysis indicates that measured dynamic stiffness contributed approximately 42% to the classification outcome, establishing it as the dominant indicator for detecting capacity deficiencies and reinforcing its physical relevance as a key health indicator for pile foundations. This study demonstrates that data-driven methods can effectively circumvent the uncertainty associated with traditional empirical coefficients, providing a promising approach to the health monitoring and rapid evaluation of in-service bridge pile foundations. Full article

Climate change poses significant threats to Mediterranean plant species, including Laurus nobilis L., an ecologically and economically important tree. This study evaluates potential shifts in its suitable distribution areas across Türkiye under future climate scenarios [Shared Socioeconomic Pathway 2-4.5 (SSP2-4.5) and 5-8.5 (SSP5-8.5)] using an ensemble species distribution model incorporating ten algorithms. Key environmental drivers—elevation, annual mean temperature (Bio1), and evaporation including sublimation and transpiration (evspsbl)—were identified as critical factors influencing habitat suitability. Results indicate substantial spatial redistributions, with habitat losses projected in inland transition zones toward continental climates, particularly in parts of the Aegean and Black Sea regions. The current suitable distribution area across the country, approximately 18.48%, could rise to 18.55% by 2040 under the SSP2-4.5 scenario and to 18.76% by 2060 under the SSP5-8.5 scenario. However, without human intervention, the species’ establishment in these new suitable distribution areas is not considered possible. Moreover, it has been determined that the suitable distribution area of the species could decrease to 17.48% by 2060 under the SSP2-4.5 scenario and to 17.31% by 2080 under the SSP5-85 scenario. This result indicates that there could be a loss of more than 8% of the suitable distribution area between 2060 and 2080, according to the SSP5-8.5 scenario. Conversely, limited expansions may occur in specific areas, including the northern Aegean and the Hatay-Antep region. By 2100, despite periodic fluctuations, a net decline in suitable habitats is expected under both scenarios. Notably, spatial analysis reveals that while some newly suitable areas may emerge, natural migration will likely be insufficient for population persistence, necessitating human-assisted adaptation strategies. These findings underscore the need for proactive conservation measures, such as identifying climate-resilient provenances, assisted migration, and targeted reforestation in future suitable zones. Given that most Turkish forests are state-managed, collaboration with the General Directorate of Forestry is essential to integrate climate adaptation into long-term management plans. This study provides a framework for mitigating climate-induced habitat loss in L. nobilis while offering insights applicable to other vulnerable Mediterranean species facing similar threats. Full article

Predicting profitable entry signals in Bitcoin markets remains challenging due to price volatility, the absence of fundamental valuation frameworks, and methodological pitfalls that are common in the literature. In this study, we evaluate five machine learning classifiers using a 37-feature hierarchical multi-timeframe pipeline with price-level-agnostic normalization across four temporal resolutions (15-min, 4-h, daily, and 3-day), spanning January 2020 to November 2025. Binary training labels were generated via majority-vote aggregation across 54 stop-loss/take-profit combinations, producing 6951 balanced samples (48.5% positive class). Five algorithms—Logistic Regression, Decision Tree, Random Forest, XGBoost, and LightGBM—are compared using expanding-window TimeSeriesSplit validation (5 folds). Random Forest achieved the highest cross-validated ROC-AUC (0.6086), with all models showing modest but consistent discriminative ability (range 0.57–0.61). Feature importance analysis identifies 4-hour Bollinger Band position and RSI as dominant predictors, with all timeframes contributing meaningfully. A true out-of-sample holdout on 1136 independently generated 2025 samples confirms generalization, with Logistic Regression achieving 0.6087 ROC-AUC. A subtle multi-timeframe look-ahead bias in higher-timeframe data alignment is identified and corrected, which inflated performance by approximately 0.20 ROC-AUC points before correction. Event-driven backtesting on 2025 out-of-sample data yields a gross upper-bound return of +35.97% (185 trades, SL = 1%, TP = 2%, threshold = 0.7, Sharpe = 0.14) before transaction costs, after realistic round-trip fees, net returns are likely negligible. The central finding is that models with ROC-AUC ≈ 0.60 cannot reliably generate economically significant returns once transaction costs are accounted for. The methodology provides a reproducible framework for ML-based binary classification studies requiring transparent, bias-corrected validation across diverse market regimes. Full article

Anxiety is a multidimensional construct that influences cognitive performance in complex ways, yet its factor structure and domain-specific effects remain unclear. This study examined (1) the psychometric structure of general and specific anxiety measures, (2) their associations with cognitive performance across different domains, and (3) the predictive power of machine learning models in classifying cognitive performance based on specific anxiety in different domains. A two-stage design was employed: Stage 1 (N = 500) assessed self-reported anxiety (trait, state, generalized, social, spatial, and math anxiety) via questionnaires, while Stage 2 (N = 104) involved a set of experiments measuring cognitive performance (accuracy and reaction time) across numerical, social, spatial, and control tasks. Factor analyses revealed a correlated yet distinct structure. The model treating anxiety measures as independent factors showed the best fit among tested alternatives; however, all CFA models exhibited suboptimal absolute fit indices (TLI/CFI < 0.73). Regression analyses also demonstrated domain-specific effects: after controlling for state and generalized anxiety, trait anxiety showed small but statistically significant positive associations with performance on the social task (OR = 1.03) and spatial task (OR = 1.07). Machine learning models (Random Forest, Decision Trees, SVM) demonstrated limited predictive accuracy, with ensemble methods outperforming linear models. Prediction of reaction time in cognitive tasks, based on anxiety measures, was less powerful, suggesting that non-anxiety factors play a larger role in cognitive performance. These findings highlight the importance of distinguishing between general and domain-specific anxieties in cognitive research and demonstrate the potential of a machine learning approach in modeling anxiety–performance relationships. Full article

Temperature and humidity are the key environmental factors affecting the storage life of seeds. To explore the feasibility and factors influencing ultra-dry storage of Pinus kesiya var. langbianensis seeds, the seeds were dehydrated to six different moisture contents (0.92–6.12%) and stored for one year. The effects of moisture content, packaging method, storage temperature, and pre-humidification method on the viability of ultra-dry seeds were systematically investigated using an orthogonal experimental design. The germination energy, relative electrical conductivity (REC), malondialdehyde (MDA), proline (Pro), total soluble sugar content, and fatty acid composition were determined. The results showed that moisture content and pre-humidification had significant effects on seed germination energy and vigor (p < 0.01). The germination energy of ultra-dried seeds was significantly negatively correlated with REC and MDA contents (p < 0.01) and significantly positively correlated with Pro content (p < 0.01). Based on the comprehensive indices, the optimal combination for seed germination energy was: 4.24% moisture content, self-sealing bag packaging, room temperature (25 °C) storage, and 20% polyethylene glycol (PEG) pre-humidification. Under the optimal moisture content (4.24%), the total sugar content of seeds was the lowest, while the fatty acid unsaturation index and oleic acid content were higher than those in the other treatments. Therefore, appropriate ultra-dry treatment can effectively maintain the seed vigor of P. kesiya var. langbianensis, and its protective effect is closely related to reducing membrane lipid peroxidation, accumulating proline, and regulating fatty acid unsaturation. This has important implications for forest seed conservation and germplasm management, particularly for long-term ex situ preservation of tree seeds in gene banks, supporting reforestation and biodiversity restoration efforts. Full article

The forest dormouse (Dryomys nitedula) is a small, nocturnal, arboreal rodent widely distributed across Central and Eastern Europe. Yet, it remains one of the least studied European glirid species, with information on its ecology in southern populations being scarce. This study presents the first systematic investigation of the diel (24 h) activity patterns of D. nitedula in Greece. From March to December 2024, camera traps were deployed on trees facing branches or artificial nest boxes at 26 locations within a 30 ha forest–meadow mosaic in Northern Greece. Based on 958 independent detections at 22 sites, activity was highest at nest boxes and exhibited two nocturnal peaks that were consistent across seasons: a major one around midnight and a secondary one before sunrise. Temporal activity overlap between nest-box cameras and branch-facing cameras was high across all seasons. Activity, measured as the number of independent detections per night, was highest during short, humid nights with low levels of moonlight. Temperature and precipitation were not good predictors of activity levels. These findings confirm that the behavior of D. nitedula is predominantly nocturnal and reveal key environmental drivers shaping its activity in the Mediterranean region. Moreover, this study highlights the value of camera trapping as a non-invasive method for monitoring small arboreal mammals and provides essential baseline data for future ecological and conservation research on this understudied species. Full article

The aim of this study was to examine the potential of multispectral imaging derived from unmanned aerial vehicles (UAVs) for detecting the spread of mistletoe (Viscum album ssp. austriacum L.) in Scots pine stands and to assess the information potential of selected vegetation indices in mistletoe detection. UAV campaigns were performed in the Niepołomice Primeval Forest (Niepołomice Forest District, Regional Directorate of the Polish State Forests National Holding, Kraków, Poland). A fixed-wing UAV Trinity F90+ (Quantum Systems GmbH) equipped with a five-band multispectral MicaSense RedEdge-M camera and an RGB Sony UMC-R10C camera was employed. The number of trees infected by mistletoe, as well as the quantity and area of mistletoe biogroups, were derived based on the classification of true multispectral orthophotos using a support vector machine (SVM) classifier. The spectral information potential assessment identified NIR (B5) as the most important single spectral source of information, while the greatest information potential among vegetation indices was found in NormG, CIG, and GRVI. The mistletoe classification of the 22.5-ha compartment revealed 1735 mistletoe biogroups covering a total area of 489 m², with 58.6% of the 2917 detected tree crowns identified as infected (Kappa = 0.74). The results confirm that UAV-based multispectral data, particularly when combined with green-sensitive vegetation indices, enable effective differentiation of mistletoe from host tree crowns. The integration of the near-infrared (NIR) band further enhanced classification performance. This study evaluates UAV-based multispectral and RGB imagery for detecting common mistletoe (Viscum album ssp. austriacum) in Scots pine stands. The information potential of 22 vegetation indices was assessed to identify the most effective spectral features for mistletoe classification. Full article