Search Results (4,174)

Urban waterlogging has become a critical challenge to urban sustainability under the combined pressures of rapid urbanization and increasingly frequent extreme weather events. However, traditional predictive models struggle to achieve real-time, point-specific early warning effectively, primarily due to the interference of redundant high-dimensional data and the inability to handle severe data imbalance. This study proposes a lightweight and interpretable machine learning framework for real-time waterlogging hotspot prediction, based on a multi-dimensional feature space. Specifically, we implement a Lasso-based mechanism to distill 37 multi-source variables into five core determinants. This process effectively isolates dominant environmental drivers while filtering noise. To further overcome the recall bottleneck, we propose a Synthetic Minority Over-sampling Technique based on Weighted Distance and Cleaning (SMOTE-WDC) algorithm that incorporates weighted feature distances and density-based noise cleaning. Validating the framework on datasets from Shenzhen (2023–2024), we demonstrate that the integrated Gradient Boosting Decision Tree (GBDT) model integrated with this strategy achieves optimal performance using only five features, yielding an F1-score of 0.808 and an Area Under the Precision-Recall Curve (AUC-PR) of 0.895. Notably, a Recall of 0.882 is attained, representing a 4.6% improvement over the baseline. This study contributes a cost-effective, high-sensitivity approach to disaster risk reduction, advancing predictive urban waterlogging management. Full article

Leaf nitrogen concentration (LNC) exhibits pronounced vertical heterogeneity across canopy layers, which affects the accuracy of nitrogen diagnosis derived from UAV-based remote sensing imagery. To address the differential contributions of leaf nitrogen from distinct canopy strata and the limitations associated with single-source features, this study proposes an integrated framework that combines cumulative LNC indicators across canopy layers with multi-source feature sets (vegetation indices and texture features). Centered on three core technical innovations—(1) incorporating canopy-layer aggregation logic into LNC modeling, (2) integrating spectral and structural information through CNN-based feature fusion, and (3) combining deep feature extraction with gradient boosting regression to improve robustness under multi-stage conditions—the framework systematically evaluates three machine learning algorithms: Random Forest (RF), a Convolutional Neural Network–Extreme Gradient Boosting hybrid model (CNN_XGBoost), and K-Nearest Neighbor (KNN) for cotton LNC estimation across multiple growth stages. The results demonstrate that cumulative canopy-layer nitrogen indicators more effectively represent overall plant nitrogen status than single-layer measurements. The integration of multi-source features further enhances model performance. Under both single-variable inputs and combined VI–TF feature sets, the CNN_XGBoost model consistently outperforms the other models in calibration accuracy and stability across all growth stages. Its optimal performance occurs during the cotton flowering and boll stage, achieving a calibration R² of 0.921. Overall, the proposed framework substantially improves the estimation accuracy of cotton LNC and provides both a theoretical foundation and technical support for precision nitrogen management and sustainable agricultural development. Full article

High-precision sediment distribution maps are indispensable for nearshore sediment dynamics and ecology and nearshore resource management. Using grain-size data of surface sediments from the nearshore waters of Lianyungang and auxiliary datasets including bathymetric and hydrodynamic conditions, this study assessed Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) for predicting sediment grain-size fractions and mapping sediment substrate types. All three models capture the spatial gradient of sediment grain size from fine to coarse from the nearshore to the offshore regions, but differ in preserving local heterogeneity and defining transition boundaries: XGBoost delivers the most balanced performance by preserving grain-size variability, reducing boundary mixing, and improving the identification of classes with limited samples; RF excels in robust delineation of gradual transitions, whereas SVR tends to produce fragmented boundaries and unstable performance for classes with limited samples. Feature importance reveals that hydrodynamic drivers dominate the spatial distribution of sand, whereas terrain indices are more influential for the clay distribution pattern, confirming the role of microtopography in modulating fine-sediment trapping. Overall, this study improves mapping accuracy and supports marine spatial planning and coastal infrastructure design. Full article

Nitrogen is one of the essential nutrient elements that affect rice growth, yield, and quality formation. Accurate and timely estimation of rice nitrogen status is fundamental for precision fertilization in agricultural fields. Hyperspectral remote sensing technology provides a promising approach for rapid and accurate acquisition of nitrogen status of rice in the field. However, traditional single-angle hyperspectral observations are easily disturbed by factors such as canopy structure, light direction, and background reflection, limiting their inversion accuracy and stability. This study is based on multi-angle polarimetric hyperspectral data obtained from an unmanned aerial vehicle platform. It extracts features from multi-angle polarimetric spectra based on three algorithms: successive projections algorithm (SPA), competitive adaptive reweighted sampling, and relevant features. The input weight and hidden layer bias of the extreme learning machine (ELM) model were optimized by the whale optimization algorithm (WOA) and caterpillar fungus optimization algorithm (CFO), taking the sensitive band of optimal viewing angle as input. Finally, an inversion model of rice canopy nitrogen content (CNC) based on multi-angle polarization hyperspectral data was established. The results demonstrate that the inversion results of the combination of SPA-(30°) + SPA-(45°) observation angles and feature selection methods are optimal, and multi-angle fusion significantly improves the model’s ability to characterize CNC, with higher stability and accuracy than single-angle modeling. The R² of CFO-ELM on the training set and test set reach 0.8553 and 0.8274, respectively, which is significantly better than the original ELM and WOA-ELM, becoming the optimal CNC inversion model in this study. The rice CNC inversion model based on multi-angle polarimetric hyperspectral data constructed in this study provides a specific reference for the rapid detection of rice CNC. Full article

Antibody–drug conjugates (ADCs) comprise a monoclonal antibody covalently bound to a cytotoxic payload by a linker. ADCs minimize off-target effects on healthy tissues, leveraging the specificity of monoclonal antibodies to deliver cytotoxic drugs to the intended tumor site. ADCs can be prone to poor behavior, including aggregation and misfolding, leading to poor efficacy, impaired pharmacokinetics, and immunogenicity. It is advantageous to understand the developability and potential liabilities of a protein candidate prior to costly in vivo studies or clinical trials. This review summarizes biophysical and structural techniques used to characterize ADCs and introduces emerging techniques aimed at accurately assessing the developability of protein candidates. Stability is commonly assayed using techniques like differential scanning calorimetry (DSC), differential scanning fluorimetry (DSF), or spectroscopic probes such as circular dichroism and intrinsic fluorescence. Drug-to-antibody ratio (DAR) is a critical parameter that can be measured using absorbance spectroscopy or chromatographic analysis. Aggregation and self-association can be probed using scattering techniques such as dynamic light scattering (DLS), static light scattering (SLS), and size exclusion chromatography–multi-angle light scattering (SEC-MALS), as well as more specialized approaches such as fluorescence correlation spectroscopy (FCS) and analytical ultracentrifugation (AUC). Mass spectrometry (MS) provides extremely valuable insight into stability, covalent modifications, and, through approaches like hydrogen–deuterium exchange (HDX-MS), structural dynamics of ADCs. Looking forward, the use of biophysical assays in ex vivo matrices and strategic use of artificial intelligence/machine learning (AI/ML) approaches are likely to advance the efficient and rapid development of ADCs and other next-generation protein therapeutics. Full article

This study explores the interconnection between the variables of ChatGPT usage, energy consumption, water consumption, and carbon dioxide CO₂ emissions. A new integer and fractional order model using the Caputo derivative is proposed to comprehend the long-term dependencies of these variables. Boundedness, and global and local stability are examined for the fractional order model. The equilibrium points of these variables are shown to determine the stability of the model. The Runge–Kutta 7 numerical method is employed for the integer order model, whereas the semi-implicit linear interpolation (L1) method is used for the fractional order model. The parameter sensitivity is conducted on the system’s parameters to understand the variables’ impact by varying the relevant parameters for the system. To increase the efficacy of our analysis, we used machine learning approaches to model and predict the dynamics of CO₂ emissions, energy and water consumption, and ChatGPT usage. The Prophet ML model stood out among the other methods because it is adept at identifying long-term growth trends, seasonal changes, and the impact of outside variables in intricate time-series data. It is extremely beneficial for research centered on sustainability, where accurate projections are essential for wellinformed decision-making, because it can produce robust, interpretable forecasts against missing values and outliers. Using the Prophet ML model, our research guarantees precise and expandable predictions and provides valuable information that can direct tactics to balance environmental sustainability and technological progress. Full article

Accurate pavement performance prediction is critical for effective pavement management systems (PMS), enabling optimal maintenance and rehabilitation decisions. The Pavement Condition Index (PCI) is the most widely used performance indicator, yet reliable prediction requires models that capture full spectrum of deterioration drivers, including structural characteristics, traffic loads, and the increasingly impactful extreme climate events. While machine learning (ML) approaches have improved PCI prediction, most existing models overlook climate extremes. This study proposes a comprehensive ML-based PCI model that integrates extreme climate variables from the Expert Team on Climate Change Detection and Indices (ETCCDI). Eleven algorithms were evaluated on a dataset combining pavement age, structural characteristics, traffic loads, and extreme climate variables. Among the evaluated models, categorical boosting model achieved the lowest error values and the highest R² (0.81). Explainability analyses using feature importance and SHapley Additive exPlanations (SHAP) identified the number of icing days (ID), daily temperature range in December (DTR_Dec) and consecutive dry days (CDD) as the extreme climate indicators with the greatest negative predictive influence on PCI. Incorporating ETCCDI indices provided additional explanatory power beyond traditional annual average climatic variables, significantly improving both predictive accuracy and model interpretability. These findings highlight the importance of integrating standardized extreme climate indicators into PMS frameworks to support more resilient and sustainable pavement management under evolving climate conditions. Full article

Glaciers in the Canadian Arctic Archipelago (CAA) contribute significantly to sea-level rise, yet sparse in situ data limit regional climate assessments. This study presents the first decadal (2013–2024) satellite-derived time series of late-summer snowline altitude (SLA) for six CAA glaciers, utilising 9920 Landsat 8/9 and Sentinel-2 scenes. Glacier surface cover types (snow and bare ice) were mapped via machine learning, and SLA was extracted using elevation-binning and Snow-Elevation Histogram Analysis (SEHA). Elevation data were obtained from ArcticDEM v3; positive degree days (PDD) from Eureka, Pond Inlet, and Pangnirtung were used to characterize melt-season forcing. Satellite-derived SLA was validated against equilibrium-line altitude (ELA) observations from White Glacier. All glaciers exhibit a characteristic seasonal SCA cycle: maximum extent in June, minimum in August, and partial recovery in September, with extreme anomalies in 2020. Annual peak SLA correlates positively with summer warmth; sensitivities to PDD were 2.56, 0.67, and 0.83 m (°C d)⁻¹ for White, Highway, and Turner glaciers, respectively. Hypsometry strongly modulates climatic sensitivity: glaciers with limited high-elevation area (e.g., BylotD20s, Turner) frequently lose their accumulation zones in warm years. At White Glacier, SLA replicates interannual ELA variability with high correlation and lower error using the elevation-bin method (mean bias +53 m; RMSE 177 m) compared with SEHA (+165 m; 339 m). Meteorological records indicate significant summer and winter warming at Eureka, with increasing PDD; precipitation trends are spatially variable. A regionally calibrated, quality-assured elevation-bin method produces objective and transferable SLA time series, suitable for ELA estimation in data-sparse Arctic settings. The SLA–PDD relationship and hypsometry-dependent responses highlight increasing stress on accumulation zones under continued warming. Reporting SLA uncertainty and image quality, alongside expanded field observations, will enhance Arctic-wide glacier monitoring. Full article

Credit risk prediction is essential for financial institutions to effectively assess the likelihood of borrower defaults and manage associated risks. This study presents a comparative analysis of deep learning architectures and traditional machine learning models on imbalanced credit risk datasets. To address class imbalance, we employ three resampling techniques: Synthetic Minority Over-sampling Technique (SMOTE), Edited Nearest Neighbors (ENN), and the hybrid SMOTE-ENN. We evaluate the performance of various models, including multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), logistic regression, decision tree, support vector machine (SVM), random forest, adaptive boosting, and extreme gradient boosting. The analysis reveals that SMOTE-ENN combined with MLP achieves the highest F1-score of 0.928 (accuracy 95.4%) on the German dataset, while SMOTE-ENN with random forest attains the best F1-score of 0.789 (accuracy 82.1%) on the Taiwanese dataset. SHapley Additive exPlanations (SHAP) are employed to enhance model interpretability, identifying key drivers of credit default. These findings provide actionable guidance for developing transparent, high-performing, and robust credit risk assessment systems. Full article

Optimizing nitrogen (N) fertilization is essential for sustaining durum wheat yield and grain quality while reducing the environmental impacts associated with N over-application. Hyperspectral sensing provides a rapid and non-destructive approach for monitoring crop N status. However, high-dimensional data, phenology-dependent spectral responses, and spatial autocorrelation in field measurements limit robust nitrogen classification and interpretation. This study evaluated hyperspectral-based nitrogen status classification in durum wheat under Mediterranean field conditions and identified key spectral regions using explainable artificial intelligence. A field experiment was conducted in Southern Italy using ten N fertilization rates (0–180 kg N ha⁻¹). Canopy reflectance was acquired at the booting and heading stages from georeferenced sampling locations. Three nitrogen stratification strategies (binary Low–High, Extreme, and three-level) were evaluated using Random Forest, SVM-RBF, and XGBoost classifiers. Model performance was assessed using spatially independent Leave-One-Plot-Out cross-validation at both the sample and plot levels, with plot-level predictions derived through majority voting. Classification robustness was strongly influenced by the stratification strategy and phenological stage. The binary Low–High stratification achieved the highest sample-level accuracy, with a maximum of 0.78 at booting (SVM-RBF) and 0.75 at heading (SVM-RBF), whereas the Extreme stratification produced intermediate performance, with maximum accuracies of 0.73 at booting (SVM-RBF) and 0.63 at heading (XGBoost). Plot-level aggregation improved performance, reaching up to 0.90 at booting and 1.00 at heading. SHAP analysis highlighted red, red-edge, and near-infrared wavelengths as the dominant contributors, with increased reliance on longer wavelengths at the heading. Overall, explainable machine learning provides a robust framework for hyperspectral nitrogen monitoring in durum wheat. Full article

Under the dual pressures of global warming and high-density urbanization, extreme heatwaves have emerged as a critical ecological risk constraining the sustainable development of Chinese urban agglomerations. Based on multi-source remote sensing, meteorological, and economic data for 19 major urban agglomerations from 2014 to 2023, this study develops an emerging industrial agglomeration–energy activity–thermal environment response framework. Using XGBoost-SHAP interpretable machine learning and GeoSHAPLEY spatial decomposition, the nonlinear and spatially heterogeneous impacts of industrial agglomeration on heatwave characteristics are systematically quantified. Results indicate that the heatwave index increased from 0.619 to 0.637, with the model explaining 80.7 percent and 74.7 percent of variance in duration and frequency, respectively. Moreover, emerging industrial agglomeration ranks among the top contributors to both duration and frequency, explaining over 20 percent of duration variability and surpassing traditional industrial and socioeconomic factors. Heatwave duration and frequency exhibit nonlinear relationships. During early agglomeration, energy efficiency improvements generated marginal cooling of five to eight percent, whereas intensified agglomeration amplifies duration by over ten percent through energy-intensive activities and infrastructure heat islands. Meanwhile, green innovation at high agglomeration levels mitigates six to nine percent of the warming effect. In addition, spatial differentiation of industrial agglomeration, reflected by a Gini increase from 0.685 to 0.728 and inter-regional contribution around 62 percent, underpins heat risk heterogeneity. Furthermore, natural endowments, socioeconomic development, infrastructure, environmental regulation, and technological innovation significantly moderate these effects, with high-tech innovation attenuating heatwave amplification. Consequently, the thermal effects of industrial agglomeration follow a three-stage spatial evolution of warming, stabilization, and counter-regulation. These findings highlight that coordinated optimization of industrial spatial layout and green technological innovation is crucial for enhancing climate resilience and promoting low-carbon transformation in urban agglomerations. Full article

Landslides are characterized by strong suddenness and a wide range of damage; accurate prediction of their susceptibility is an important prerequisite for regional risk prevention and control. To address the difficulties in acquiring landslide inventories in complex terrain areas and the insufficient interpretability of existing prediction models, this study proposes a landslide susceptibility assessment (LSA) framework that integrates automated sample detection and interpretability analysis. The proposed framework is applied to Moxi Town, a typical alpine valley area in Sichuan Province, China. A Mask R-CNN instance segmentation model was introduced to achieve automated detection of landslide samples, resulting in a high-quality inventory containing 923 landslides. Based on the spatial relationships between the landslide inventory and influencing factors, a convolutional neural network (CNN) landslide susceptibility assessment model incorporating Shapley Additive exPlanations (SHAP) interpretability analysis was constructed. The CNN model was further compared with random forest (RF) and extreme gradient boosting (XGBoost) machine learning models. The results show that the AUC value of the CNN model has increased by 4.3% and 3.2% compared with the RF and XGBoost models, respectively, and it significantly reduces the pretzel effect of landslide susceptibility mapping (LSM). The results validate the reliability of the proposed framework, which can provide technical support for landslide disaster prevention and monitoring. Full article

This paper addresses the problem of multi-class classification of bacterial microscopic images using a rigorous experimental protocol designed to prevent information leakage and improve performance. The dataset consists of 2034 images representing 33 taxa, organized by class. Data integrity checks confirmed the absence of corrupted or unreadable files. To formalize image characteristics and ensure quality control, indirect geometric and textural features were calculated, including minimum frame size, brightness statistics (mean and standard deviation), Shannon entropy, Laplace variance, and Sobel gradient energy. Quality checks revealed a small proportion of images with extreme brightness (2.5074%), while no samples with critically low sharpness according to the selected criteria were detected. Statistical analysis of interclass differences using the Kruskal–Wallis test with multiple comparison correction demonstrated the high discriminatory power of texture features, specifically gradient energy (ε² = 0.819987) and Laplace variance (ε² = 0.709904). Feature correlations were consistent with their physical interpretation, revealing a strong positive relationship between sharpness and gradient energy. Principal component analysis confirmed a strong structural pattern, with the first two components explaining 75.5766% of the total variance. For a unified comparison, classical machine learning, transfer learning, and modern deep architectures were evaluated within a single protocol. Full article

Aboveground biomass (AGB) is a key indicator of vegetation productivity and terrestrial carbon stocks; therefore, robust AGB estimation is critical for assessing ecosystem services and carbon cycle research. Previous studies have largely focused on forest and cropland ecosystems. In contrast, roadside vegetation along highways and other linear transport corridors remains comparatively underexplored despite its potentially important role as a carbon sink. Here, we integrate field-measured AGB samples with GF-2 high-resolution satellite imagery to evaluate the suitability of multiple remote-sensing predictors and machine-learning algorithms for estimating AGB in highway roadside vegetation. Six remote-sensing variables were used as predictors, including four vegetation indices (Normalized Difference Vegetation Index (NDVI), Perpendicular Vegetation Index (PVI), Enhanced Vegetation Index (EVI), and Modified Soil-Adjusted Vegetation Index (MSAVI) and two-band ratios (B342 and B12/34). Five regression models—multiple linear regression (MLR), partial least squares regression (PLSR), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost)—were developed and systematically compared under both single-variable and multi-variable scenarios. Model performance was evaluated using five-fold cross-validation, with the coefficient of determination (R²) and the root mean square error (RMSE) as metrics of evaluation. The results indicate that the RF model under the multi-variable scenario achieved the best overall performance, with a training R² of 0.83 and a testing RMSE of 0.84 kg·m⁻², substantially outperforming the other linear and non-linear models. The optimal RF model was further applied to GF-2 imagery to produce a spatially explicit AGB map for a 32 km highway segment and a 30 m roadside buffer on both sides, yielding an estimated total aboveground biomass of 566.97 t for the corridor. These findings demonstrate that combining high-resolution remote sensing with machine-learning approaches can effectively improve AGB estimation for linear roadside vegetation systems, providing technical support for ecological monitoring, roadside greening management, and carbon accounting for transport infrastructure. Full article

The growing need for sustainable and lightweight building materials has accelerated research on alternatives to conventional concretes, out of which Lightweight Expanded Clay Aggregate (LECA) concrete has emerged as a promising solution. However, the high porosity and nonlinear mechanical behavior of LECA concrete complicate the accurate prediction of compressive strength through conventional empirical models. The main focus of the paper is on identifying a comprehensive machine learning-based framework for modeling and predicting the 28-day compressive strength of LECA-based lightweight concrete. The dataset was created and preprocessed by using statistical normalization and correlation analysis. In this study, five supervised machine learning models—Multiple Linear Regression (MLR), Support Vector Regression (SVR), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost)—were developed and fine-tuned using a grid-search strategy combined with ten-fold cross-validation. The quality of the prediction made by each model was evaluated by means of standard performance indicators, such as the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). After the evaluation, the models were subsequently compared and ranked according to the Gray Relational Analysis (GRA) method. The comparative assessment shows that CatBoost demonstrated the most reliable performance, achieving an R² of 0.907, RMSE of 3.41 MPa, MAE of 2.47 MPa, and MAPE of 10.05%, outperforming the remaining algorithms. To interpret the significance of features, SHAP (Shapley Additive exPlanations) analysis was applied, which identified water and LECA content as the dominant factors influencing compressive strength, followed by the cement and fine aggregate proportions. The findings reveal that the ensemble-based gradient boosting model is capable of capturing intricate nonlinear interactions, as observed in the heterogeneous matrix of LECA concrete. Full article