Search Results (215)

Wetland mapping plays a crucial role in monitoring wetland ecosystems, water resource management, and habitat suitability assessment. Wetland classification remains significantly challenging due to the diverse types, intricate spatial patterns, and highly dynamic nature. This study proposed a dynamic hybrid method that integrated feature selection and object-oriented ensemble model construction to improve wetland mapping using Sentinel-1 and Sentinel-2 data. The proposed feature selection approach integrates the ReliefF and recursive feature elimination (RFE) algorithms with a feature evaluation criterion based on Shapley additive explanations (SHAP) values, aiming to optimize the feature set composed of various variables. During the construction of ensemble models (i.e., RF, XGBoost, and LightGBM) with features selected by RFE, hyperparameter tuning is subsequently conducted using Bayesian optimization (BO), ensuring that the selected optimal features and hyperparameters significantly enhance the accuracy and performance of the classifiers. The accuracy assessment demonstrates that the BO-LightGBM model with ReliefF-RFE-SHAP-selected features achieves superior performance to the RF and XGBoost models, achieving the highest overall accuracy of 89.4% and a kappa coefficient of 0.875. The object-oriented classification maps accurately depict the spatial distribution patterns of different wetland types. Furthermore, SHAP values offer global and local interpretations of the model to better understand the contribution of various features to wetland classification. The proposed dynamic hybrid method offers an effective tool for wetland mapping and contributes to wetland environmental monitoring and management. Full article

Abdominal fat is a key indicator of chicken meat quality. Excessive deposition not only reduces meat quality but also decreases feed conversion efficiency, making the breeding of low-abdominal-fat strains economically important. Genomic selection (GS) uses information from genome-wide association studies (GWASs) and high-throughput sequencing data. It estimates genomic breeding values (GEBVs) from genotypes, which enables early and precise selection. Given that abdominal fat is a polygenic trait controlled by numerous small-effect loci, this study combined population genetic analyses with machine learning (ML)-based feature selection. Relevant single-nucleotide polymorphisms (SNPs) were first identified using a combined GWAS and linkage disequilibrium (LD) approach, followed by a two-stage feature selection process—Lasso for dimensionality reduction and recursive feature elimination (RFE) for refinement—to generate the model input set. We evaluated multiple machine learning models for predicting genomic estimated breeding values (GEBVs). The results showed that linear models and certain nonlinear models achieved higher accuracy and were well suited as base learners for ensemble methods. Building on these findings, we developed a Dynamic Adaptive Weighted Stacking Ensemble Learning Framework (DAWSELF), which applies dynamic weighting and voting to heterogeneous base learners and integrates them layer by layer, with Ridge serving as the meta-learner. In three independent validation populations, DAWSELF consistently outperformed individual models and conventional stacking frameworks in prediction accuracy. This work establishes an efficient GEBV prediction framework for complex traits such as chicken abdominal fat and provides a reusable SNP feature selection strategy, offering practical value for enhancing the precision of poultry breeding and improving product quality. Full article

Soil salinization poses a severe threat to agricultural sustainability in the Yellow River Delta, where conventional spectral indices are limited by vegetation interference and seasonal dynamics in coastal saline-alkali landscapes. To address this, we developed an inversion framework integrating spectral indices and vegetation temporal features, combining multi-temporal Sentinel-2 optical data (January 2024–March 2025), Sentinel-1 SAR data, and terrain covariates. The framework employs Savitzky–Golay (SG) filtering to extract vegetation temporal indices—including NDVI temporal extremum and principal component features, capturing salt stress response mechanisms beyond single-temporal spectral indices. Based on 119 field samples and Variable Importance in Projection (VIP) feature selection, three ensemble models (XGBoost, CatBoost, LightGBM) were constructed under two strategies: single spectral features versus fused spectral and vegetation temporal features. The key results demonstrate the following: (1) The LightGBM model with fused features achieved optimal validation accuracy (R² = 0.77, RMSE = 0.26 g/kg), outperforming single-feature models by 13% in R². (2) SHAP analysis identified vegetation-related factors as key predictors, revealing a negative correlation between peak biomass and salinity accumulation, and the summer crop growth process affects soil salinization in the following spring. (3) The fused strategy reduced overestimation in low-salinity zones, enhanced model robustness, and significantly improved spatial gradient continuity. This study confirms that vegetation phenological features effectively mitigate agricultural interference (e.g., tillage-induced signal noise) and achieve high-resolution salinity mapping in areas where traditional spectral indices fail. The multi-temporal integration framework provides a replicable methodology for monitoring coastal salinization under complex land cover conditions. Full article

Reliable, high-resolution emission inventories are essential for accurately simulating air quality and for designing evidence-based mitigation policies. Yet their performance over Japan—where transboundary inflow, strict fuel regulations, and complex source mixes coexist—remains poorly quantified. This study therefore benchmarks four widely used anthropogenic inventories—REAS v3.2.1, CAMS-GLOB-ANT v6.2, ECLIPSE v6b, and HTAP v3—by coupling each to WRF-Chem (10 km grid) and comparing simulated surface PM₂.₅, SO₂, CO, and NO_x with observations from >900 stations across eight Japanese regions for the years 2010 and 2015. All simulations shared identical meteorology, chemistry, and natural-source inputs (MEGAN 2.1 biogenic VOCs; FINN v1.5 biomass burning) so that differences in model output isolate the influence of anthropogenic emissions. HTAP delivered the most balanced SO₂ and CO fields (regional mean biases mostly within ±25%), whereas ECLIPSE reproduced NO_x spatial gradients best, albeit with a negative overall bias. REAS captured industrial SO₂ reliably but over-estimated PM₂.₅ and NO_x in western conurbations while under-estimating them in rural prefectures. CAMS-GLOB-ANT showed systematic biases—under-estimating PM₂.₅ and CO yet markedly over-estimating SO₂—highlighting the need for Japan-specific sulfur-fuel adjustments. For several pollutant–region combinations, absolute errors exceeded 100%, confirming that emissions uncertainty, not model physics, dominates regional air quality error even under identical dynamical and chemical settings. These findings underscore the importance of inventory-specific and pollutant-specific selection—or better, multi-inventory ensemble approaches—when assessing Japanese air quality and formulating policy. Routine assimilation of ground and satellite data, together with inverse modeling, is recommended to narrow residual biases and improve future inventories. Full article

Gross primary productivity (GPP) is a key indicator for assessing carbon uptake capacity and photosynthetic productivity in agricultural ecosystems, playing a crucial role in regional carbon cycle evaluation and sustainable agriculture development. However, traditional mechanistic light use efficiency (LUE) models exhibit variable accuracy under different climatic conditions and crop types. Machine learning models, while demonstrating strong fitting capabilities, heavily depend on the selection of input features and data availability. This study focuses on winter wheat in the Guanzhong region, utilizing continuous field observation data from the 2020–2022 growing seasons to develop five machine learning models: Ridge Regression (Ridge), Random Forest (RF), Support Vector Regression (SVR), Gradient Boosting Regression (GB), and a stacking-based ensemble learning model (LSM). These models were compared with the LUE model under two scenarios, excluding and including solar-induced chlorophyll fluorescence (SIF), to evaluate the contribution of SIF to GPP estimation accuracy. The results indicate significant differences in GPP estimation performance among the machine learning models, with LSM outperforming others in both scenarios. Without SIF, LSM achieved an average R² of 0.87, surpassing individual models (0.72–0.83), demonstrating strong stability and generalization ability. With SIF inclusion, all machine learning models showed marked accuracy improvements, with LSM’s average R² rising to 0.91, highlighting SIF’s critical role in capturing photosynthetic dynamics. Although the LUE model approached machine learning model accuracy in some growth stages, its overall performance was limited by structural constraints. This study demonstrates that ensemble learning methods integrating multi-source observations offer significant advantages for high-precision winter wheat GPP estimation, and that incorporating SIF as a physiological indicator further enhances model robustness and predictive capacity. The findings validate the potential of combining ensemble learning and photosynthetic physiological parameters to improve GPP retrieval accuracy, providing a reliable technical pathway for agricultural ecosystem carbon flux estimation and informing strategies for climate change adaptation. Full article

Conformational heterogeneity is essential for protein function, yet validating theoretical molecular dynamics (MD) ensembles remains a significant challenge. In this study, we present an approach that integrates free MD simulations, starting from an AlphaFold-generated structure, with refined experimental NMR-relaxation data to identify biologically relevant holistic time-resolved 4D conformational ensembles. Specifically, we select trajectory segments (RMSD plateaus) consistent with experimental observables. For the extracellular region of Streptococcus pneumoniae PsrSp, we found that only specific segments of the long MD trajectory aligned well with experimental data. The resulting ensembles revealed two regions with increased flexibility, both of which play important functional roles. Full article

With the significant increase in solar power generation’s proportion in power systems, the uncertainty of its power output poses increasingly severe challenges to grid operation. In recent years, solar forecasting models have achieved remarkable progress, with various developed models each exhibiting distinct advantages and characteristics. To address complex and variable geographical and meteorological conditions, it is necessary to adopt a multi-model fusion approach to leverage the strengths and adaptability of individual models. This paper proposes a photovoltaic power prediction framework based on multi-stage ensemble learning, which enhances prediction robustness by integrating the complementary advantages of heterogeneous models. The framework employs a three-level optimization architecture: first, a recursive feature elimination (RFE) algorithm based on LightGBM–XGBoost–MLP weighted scoring is used to screen high-discriminative features; second, mutual information and hierarchical clustering are utilized to construct a heterogeneous model pool, enabling competitive intra-group and complementary inter-group model selection; finally, the traditional static weighting strategy is improved by concatenating multi-model prediction results with real-time meteorological data to establish a time-period-based dynamic weight optimization module. The performance of the proposed framework was validated across multiple dimensions—including feature selection, model screening, dynamic integration, and comprehensive performance—using measured data from a 75 MW photovoltaic power plant in Inner Mongolia and the open-source dataset PVOD. Full article

Owing to its excellent crack resistance and durability, High-Performance Fiber-Reinforced Concrete (HPFRC) has been extensively applied in engineering structures exposed to extreme loading conditions. The Mode I dynamic fracture strength of HPFRC under high-strain-rate conditions exhibits significant strain-rate sensitivity and nonlinear response characteristics. However, existing experimental methods for strength measurement are limited by high costs and the absence of standardized testing protocols. Meanwhile, conventional data-driven models for strength prediction struggle to achieve both high-precision prediction and physical interpretability. To address this, this study introduces a dynamic fracture strength prediction method based on a feature-weighted linear ensemble (FWL) mechanism. A comprehensive database comprising 161 sets of high-strain-rate test data on HPFRC fracture strength was first constructed. Key modeling variables were then identified through correlation analysis and an error-driven feature selection approach. Subsequently, six representative machine learning models (KNN, RF, SVR, LGBM, XGBoost, MLPNN) were employed as base learners to construct two types of ensemble models, FWL and Voting, enabling a systematic comparison of their performance. Finally, the predictive mechanisms of the models were analyzed for interpretability at both global and local scales using SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) methods. The results demonstrate that the FWL model achieved optimal predictive performance on the test set (R² = 0.908, RMSE = 2.632), significantly outperforming both individual models and the conventional ensemble method. Interpretability analysis revealed that strain rate and fiber volume fraction are the primary factors influencing dynamic fracture strength, with strain rate demonstrating a highly nonlinear response mechanism across different ranges. The integrated prediction framework developed in this study offers the combined advantages of high accuracy, robustness, and interpretability, providing a novel and effective approach for predicting the fracture behavior of HPFRC under high-strain-rate conditions. Full article

The complex topography of China’s Tibetan Plateau mountainous roads, characterized by diverse curve types and frequent traffic accidents, significantly impacts the safety and sustainability of the transportation system. To enhance driving safety on these mountain roads and promote low-carbon, resilient transportation development, this study investigates the mechanisms through which different curve types affect driving safety and proposes optimization strategies based on interpretable machine learning methods. Focusing on three typical curve types in plateau regions, drone high-altitude photography was employed to capture footage of three specific curves along China’s National Highway G318. Oblique photography was utilized to acquire road environment information, from which 11 data indicators were extracted. Subsequently, 8 indicators, including cornering preference and vehicle type, were designated as explanatory variables, the curve type indicator was set as the dependent variable, and the remaining indicators were established as safety assessment indicators. Linear models (logistic regression, ridge regression) and non-linear models (Random Forest, LightGBM, XGBoost) were used to conduct model comparison and factor analysis. Ultimately, three non-linear models were selected, employing an explainability-oriented dynamic ensemble learning strategy (X-DEL) to evaluate the three curve types. The results indicate that non-linear models outperform linear models in terms of accuracy and scene adaptability. The explainability-oriented dynamic ensemble learning strategy (X-DEL) is beneficial for the construction of driving safety models and factor analysis on Tibetan Plateau mountainous roads. Furthermore, the contribution of indicators to driving safety varies across different curve types. This research not only deepens the scientific understanding of safety issues on plateau mountainous roads but, more importantly, its proposed solutions directly contribute to building safer, more efficient, and environmentally friendly transportation systems, thereby providing crucial impetus for sustainable transportation and high-quality regional development in the Tibetan Plateau. Full article

Accurate prediction of geological hazard susceptibility forms the foundation of effective risk management, yet small-sample constraints often limit model generalization. In order to address this issue, this study applied an ensemble method based on predictive symmetry quantification, using Mount Tai, China, as a test case. Thirteen influencing factors were integrated using six machine learning algorithms—Logistic Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGB), and Support Vector Machine (SVM)—trained on 34 hazard sites. Symmetry breaking in model outputs was quantified, and XGB and MLP, which showed the lowest correlation (0.59), were selected for dynamic weighted integration. Symmetry-adjusted weighting counteracts bias from individual models. For hyperparameter tuning, grid search was employed, while SHapley Additive exPlanations (SHAP) was used to quantify factor contributions. The performance of each model was evaluated using AUC and AP metrics. The key results show that all base models performed robustly (AUC > 0.8), with XGB showing high consistency (AUC = 0.927), and the performance of the symmetry-optimized ensemble (MLP + XGB) exceeded that of all the individual models (AUC = 0.964). The dominant drivers of Geohazards included elevation, slope, the topographic wetness index, and road adjacency, with high-susceptibility zones clustered in southeastern high-altitude terrain, central mountains, and road-intensive north-central sectors. The approach presented here provides an ensemble method based on predictive symmetry quantification that is effective under the constraints of small sample sizes. Full article

Traditional landslide susceptibility assessment (LSA) methods typically adopt a global modeling strategy, which struggles to account for the pronounced spatial heterogeneity arising from variations in topography, geology, and vegetation conditions within a region. Furthermore, model predictive performance is often undermined by feature redundancy. To address these limitations, this study focuses on the landslide disaster early-warning demonstration area in Honghe Prefecture, Yunnan Province. It proposes an ensemble learning model termed heterogeneity feature optimized stacking (HF-stacking), which integrates spatial heterogeneity partitioning (SHP) with feature selection to improve the scientific rigor of LSA. This method initially establishes an LSA system comprising 15 static landslide conditioning factors (LCFs) and two dynamic factors representing the average annual deformation rates derived from interferometric synthetic aperture radar (InSAR) technology. Based on landslide inventory data, an SHP method combining t-distributed stochastic neighbor embedding (t-SNE) and iterative self-organizing (ISO) clustering was developed to divide the study area into subregions. Within each subregion, a tailored feature selection strategy was applied to determine the optimal feature subset. The final LSA was performed using the stacking ensemble learning approach. The results show that the HF-stacking model achieved the best overall performance, with an average AUC of 95.90% across subregions, 4.23% higher than the traditional stacking model. Other evaluation metrics also demonstrated comprehensive improvements. This study confirms that constructing an SHP framework and implementing feature selection strategies can effectively reduce the impact of spatial heterogeneity and feature redundancy, thereby significantly enhancing the predictive performance of LSA models. The proposed method contributes to improving the reliability of regional landslide risk assessments. Full article

Urban multimodal travel trajectory prediction is a core challenge in Intelligent Transportation Systems (ITSs). It requires modeling both spatiotemporal dependencies and dynamic interactions among different travel modes such as taxi, bike-sharing, and buses. To address the limitations of existing methods in capturing these diverse trajectory characteristics, we propose a spatiotemporal multi-model ensemble framework, which is an ensemble model called GLEN (GCN and LSTM Ensemble Network). Firstly, the trajectory feature adaptive driven model selection mechanism classifies trajectories into dynamic travel and fixed-route scenarios. Secondly, we use a Graph Convolutional Network (GCN) to capture dynamic travel patterns and Long Short-Term Memory (LSTM) network to model fixed-route patterns. Subsequently the outputs of these models are dynamically weighted, integrated, and fused over a spatiotemporal grid to produce accurate forecasts of urban total traffic flow at multiple future time steps. Finally, experimental validation using Beijing’s Chaoyang district datasets demonstrates that our framework effectively captures spatiotemporal and interactive characteristics between multimodal travel trajectories and outperforms mainstream baselines, thereby offering robust support for urban traffic management and planning. Full article

Contextual multi-armed bandits (CMABs) are vital for sequential decision-making in areas such as recommendation systems, clinical trials, and finance. We propose a simulation framework integrating Gaussian Process (GP)-based CMABs with vine copulas to model dependent contexts and GARCH processes to capture reward volatility. Rewards are generated via copula-transformed Beta distributions to reflect complex joint dependencies and skewness. We evaluate four policies—ensemble, Epsilon-greedy, Thompson, and Upper Confidence Bound (UCB)—over 10,000 replications, assessing cumulative regret, observed reward, and cumulative reward. While Thompson sampling and LLM-guided policies consistently minimize regret and maximize rewards under varied reward distributions, Epsilon-greedy shows instability, and UCB exhibits moderate performance. Enhancing the ensemble with copula features, GP models, and dynamic policy selection driven by a large language model (LLM) yields superior adaptability and performance. Our results highlight the effectiveness of combining structured probabilistic models with LLM-based guidance for robust, adaptive decision-making in skewed, high-variance environments. Full article

Many commercial wearable sensor systems typically rely on a single continuous cardiorespiratory sensing modality, photoplethysmography (PPG), which suffers from inherent biases (i.e., differences in skin tone) and noise (e.g., motion and pressure artifacts). In this research, we present a wearable device that provides robust estimates of cardiorespiratory variables by combining three physiological signals from the upper arm: multiwavelength PPG, single-sided electrocardiography (SS-ECG), and bioimpedance plethysmography (BioZ), along with an inertial measurement unit (IMU) providing 3-axis accelerometry and gyroscope information. We evaluated the multimodal device on 16 subjects by its ability to estimate heart rate (HR) and breathing rate (BR) in the presence of various static and dynamic noise sources (e.g., skin tone and motion). We proposed a hierarchical approach that considers the subject’s skin tone and signal quality to select the optimal sensing modality for estimating HR and BR. Our results indicate that, when estimating HR, there is a trade-off between accuracy and robustness, with SS-ECG providing the highest accuracy (low mean absolute error; MAE) but low reliability (higher rates of sensor failure), and PPG/BioZ having lower accuracy but higher reliability. When estimating BR, we find that fusing estimates from multiple modalities via ensemble bagged tree regression outperforms single-modality estimates. These results indicate that multimodal approaches to cardiorespiratory monitoring can overcome the accuracy–robustness trade-off that occurs when using single-modality approaches. Full article

While personal thermal comfort is critical for well-being and productivity, it is often overlooked by traditional building management systems that rely on uniform settings. Modern data-driven approaches often fail to capture the complex interactions between various data streams. This pilot study introduces a high-accuracy, interpretable framework for thermal comfort classification, designed to identify the most significant predictors from a comprehensive suite of environmental, physiological, and anthropometric data in a controlled group of young adults. Initially, an XGBoost model using the full 24-feature dataset achieved the best performance at 91% accuracy. However, after using SHAP analysis to identify and select the most influential features, the performance of our ensemble models improved significantly; notably, a Random Forest model’s accuracy rose from 90% to 94%. Our analysis confirmed that for this homogeneous cohort, environmental parameters—specifically temperature, humidity, and CO₂—were the dominant predictors of thermal comfort. The primary strength of this methodology lies in its ability to create a transparent pipeline that objectively identifies the most critical comfort drivers for a given population, forming a crucial evidence base for model design. The analysis also revealed that the predictive value of heart rate variability (HRV) diminished when richer physiological data, such as diastolic blood pressure, were included. For final validation, the optimized Random Forest model, using only the top 10 features, was tested on a hold-out set of 100 samples, achieving a final accuracy of 95% and an F1-score of 0.939, with all misclassifications occurring only between adjacent comfort levels. These findings establish a validated methodology for creating effective, context-aware comfort models that can be embedded into intelligent building management systems. Such adaptive systems enable a shift from static climate control to dynamic, user-centric environments, laying the critical groundwork for future personalized systems while enhancing occupant well-being and offering significant energy savings. Full article