Search Results (2,879)

Air pollution remains a major public-health concern, and exposure to particulate matter (PM), particularly PM₁₀ (with a diameter ≤ 10 µm), is associated with adverse respiratory and cardiovascular outcomes. Most research relies on a singular model for PM₁₀ surface estimation. This study is an assessment of a national-scale, daily PM₁₀ estimation framework for Lithuania (2019–2024), using a hybrid machine-learning method that combines Random Forest (RF) and extreme gradient boosting (XGBoost) algorithms. Hourly PM₁₀ observations were aggregated from 18 monitoring stations to obtain daily means and temporal means. The predictors integrated meteorological factors, such as temperature, wind, humidity, and precipitation, to determine satellite-based atmospheric composition from Sentinel-5P Tropospheric Monitoring Instruments (TROPOMI). Atmospheric components include nitrogen dioxide (NO₂), carbon monoxide (CO), sulfur dioxide (SO₂), ozone (O₃), formaldehyde (HCHO), and the absorbing aerosol index (AI). Moderate-Resolution Imaging Spectroradiometers (MODIS) were used to record land-surface temperature and static spatial descriptors, such as elevation, land cover, Normalized Difference Vegetation Index (NDVI), population, and road proximity. The dataset was partitioned temporally into training (70%), validation (20%), and testing (10%). The hybrid model achieved an improved accuracy, compared with single-model baselines, reaching a coefficient of determination (R²) of 0.739 in validation and R² = 0.75 in the tested dataset. Mean absolute error (MAE) was 3.15 µg/m³, and root mean square error (RMSE) was 3.98 µg/m³. The results indicate a slight tendency to overestimate PM₁₀ concentrations at lower concentration levels. Feature-importance analysis revealed that short-term temporal persistence is the key to daily PM₁₀ prediction, while meteorological variables provide secondary contributions. Temporal evaluation, using consecutive two-year windows, revealed a consistent improvement in predictive performance from 2019–2020 to 2023–2024, while station-level analysis showed moderate-to-strong agreement between the predicted and observed PM₁₀ concentrations across monitoring stations, with R² ranging from 0.455 to 0.760. This provides decision-support capabilities for air-quality management, the evaluation of mitigation measures, and integration of air-pollution considerations into sustainable urban planning strategies assessing public-health protection. Full article

Monitoring the freshness of Salmo salar within cold chain logistics is paramount for ensuring food safety. However, conventional physicochemical and microbiological assays are impeded by inherent limitations, including destructiveness and significant time latency, rendering them inadequate for the real-time, non-invasive inspection demands of modern industry. Here, we present a novel detection framework synergizing hyperspectral imaging (400–1000 nm) with the Transformer deep learning architecture. Through a rigorous comparative analysis of twelve preprocessing protocols and four feature wavelength selection algorithms (Lasso, Genetic Algorithm, Successive Projections Algorithm, and Random Frog), prediction models for Total Volatile Basic Nitrogen (TVB-N) and Total Viable Count (TVC) were established. Furthermore, the capacity of the Transformer to capture long-range spectral dependencies was systematically investigated. Experimental results demonstrate that the model integrating Savitzky-Golay (SG) smoothing with the Transformer yielded optimal performance across the full spectrum, achieving determination coefficients (R²) of 0.9716 and 0.9721 for the Prediction Sets of TVB-N and TVC, respectively. Following the extraction of 30 characteristic wavelengths via the Successive Projections Algorithm (SPA), the streamlined model retained exceptional predictive precision (R² ≥ 0.95) while enhancing computational efficiency by a factor of approximately six. This study validates the superiority of attention-mechanism-based deep learning algorithms in hyperspectral data analysis. These findings provide a theoretical foundation and technical underpinning for the development of cost-effective, high-efficiency portable multispectral sensors, thereby facilitating the intelligent transformation of the aquatic product supply chain. Full article

Against the backdrop of climate change and rapid urbanization, assessing urban flood resilience requires spatially continuous and interpretable approaches capable of capturing nonlinear interactions between natural and human systems. This study proposes a high-resolution framework for mapping urban flood resilience in the built-up areas of Chongqing, China, grounded in the geography–ecology–society–infrastructure systems (GESIS) concept. A Flood Resilience Index is constructed at a 50 m grid resolution using ten core indicators and objective weighting based on combined entropy and coefficient-of-variation methods. Three machine learning models—multilayer perceptron (MLP), random forest, and XGBoost—are then trained to reproduce the resilience surface by integrating these indicators with additional historical flood-exposure variables, with SHAP used for model interpretation. The MLP model achieves the best performance (R² ≈ 0.78) and generates spatially coherent resilience patterns. Impervious surface fraction and building density exert dominant negative effects, whereas elevation and ecological connectivity contribute positively. The results reveal pronounced nonlinear thresholds in key drivers, indicating that flood resilience cannot be inferred from monotonic factor effects alone. By combining objective weighting, explainable machine learning, and historical exposure information, this framework supports both accurate prediction and policy-relevant interpretation of urban flood resilience for sustainable urban planning in mountainous megacities. Full article

Globally, the swine industry is a major component of agricultural production, and the increasing scale and intensification of pig farming have heightened concerns about NH₃ emissions. As farms expand and adopt smart farming technologies, there is a need for reliable prediction of NH₃ concentrations without relying solely on costly physical sensors. In this study, we developed an artificial intelligence-based prediction model for NH₃ concentration in commercial pig houses and examined the effects of data collection intervals and learning strategies. We compared a standalone model trained only on local data with a transfer learning model that adapts a pre-trained model to a target farm with limited data. Transfer learning consistently outperformed the standalone approach across all data collection intervals (10, 20, 30 and 60 min). The best-performing Random Forest and XGBoost models achieved a coefficient of determination (R²) of 0.969, root mean square error (RMSE) of about 1.0 ppm and mean absolute percentage error (MAPE) below 5%. These results show that transfer learning can provide accurate NH₃ predictions in swine housing even with sparse data, supporting more sustainable and data-efficient environmental management. Full article

Thermal imaging, which is contact-free, light-independent, and effective in detecting skin temperature changes that reflect autonomic nervous system activity, is expected to be useful for emotion sensing. A recent thermography study demonstrated a linear relationship between ear temperatures and emotional arousal ratings. However, whether and how ear thermal changes may be nonlinearly related to subjective emotions remains untested. To address this issue, we reanalyzed a dataset that included ear thermal images and self-reported arousal ratings obtained while participants watched emotion-eliciting films. We employed linear regression and two nonlinear machine learning models: a random forest model and a ResNet-50 convolutional neural network. Model evaluation using mean squared error and correlation coefficients between actual arousal ratings and model predictions indicated that both machine learning models outperformed linear regression and that the ResNet-50 model outperformed the random forest model. Interpretation of the ResNet-50 model using Gradient-weighted Class Activation Mapping and Shapley additive explanation methods revealed nonlinear associations between temperature changes in specific ear regions and subjective arousal ratings. These findings imply that ear thermal imaging combined with machine learning, particularly deep learning, holds promise for emotion sensing. Full article

This paper proposed a stacking-based ensemble model to replace the traditional single machine learning model prediction approach, significantly improving the evaluation efficiency of SoC and SoH of lithium batteries. Firstly, a dataset was constructed including three input variables (temperature, current, and voltage) and two output variables (SoC and SoH). Pearson correlation coefficients and histograms were used for preliminary analysis of the correlations and distributions of the dataset. The multi-layer perceptron (MLP), support vector machine (SVM), random forest (RF), and extreme gradient boosting tree (XGB) were used as base prediction models. Bayesian optimization (BO) was used to fine-tune the parameters of these models, then three statistical indicators were compared to assess the prediction accuracy of the four ML models. Furthermore, MLP, SVM, and RF were selected as base models, while XGB was used as the meta-model, enhancing the integrated performance of the prediction models. SHAP was used to quantify the influence of the output variables on SoC. Finally, linked measures for the prediction model were proposed to achieve autonomous monitoring of drones. The results showed that XGB exhibited superior prediction accuracy, with R² of 0.93 and RMSE of 0.14. The ensemble model obtained using stacking reduced the number of outliers by 89.4%. Current was identified as the key variable influencing both SoC and SoH. Furthermore, the intelligent prediction model proposed in this paper can be integrated with controllers, visualization web pages, and other systems to enable the health status assessment of drones. Full article

Persistent cloud cover and frequent rainfall in subtropical regions throughout the year significantly limit the applicability of optical remote sensing for tree species identification, thereby constraining dynamic forest monitoring and precise management of forest resources. To address this challenge, this study proposes a tree species identification method that integrates multi-source remote sensing temporal features. By combining multi-temporal optical imagery from Sentinel-2 and dual-polarisation Synthetic Aperture Radar (SAR) data from Sentinel-1, we constructed a comprehensive feature set that incorporates spectral, structural, and phenological attributes, including various vegetation indices, backscatter coefficients, and polarimetric decomposition parameters. Through correlation analysis and assessment of temporal feature variability, five distinct integration strategies (T1-T5) were developed to classify six typical subtropical tree species: Pinus massoniana, Pinus elliottii, Acacia, Eucalyptus grandis, Mangrove, and Other hardwoods, using a random forest classifier. The results indicate that the multi-source feature fusion approach significantly outperforms single-source models, with the T5 strategy achieving the highest overall accuracy (OA) of 95.33% and a Kappa coefficient of 0.94. The red-edge vegetation indices and SAR polarimetric features were identified as major contributors to improving the classification accuracy of hardwood species. This study demonstrates that multi-source remote sensing data fusion can effectively mitigate the spatiotemporal constraints of optical imagery, providing a viable solution and technical framework for high-accuracy remote sensing classification in complex subtropical forest environments. Full article

Accurate prediction of wheat prices is crucial for market participants and policymakers because volatility in agricultural markets affects food security and economic planning. This study proposes a hybrid deep-learning-based framework for daily wheat price prediction in Türkiye. The approach first applies an autoencoder to detect and remove anomalous price–quality records from a dataset of 38,019 market transactions collected between June 2022 and May 2023. A weighted ensemble combining Linear Regression, Random Forest, Support Vector Regression and an attention-based Long Short-Term Memory network is then trained on quality parameters and market attributes, with data split into training, validation and test sets. On the independent test set the ensemble achieved a coefficient of determination R² = 0.9942 and a mean absolute error of 0.1646 TL, outperforming the constituent models. SHAP analysis identifies the price–quality ratio as the most influential feature, while the ablation analysis shows that some of the high accuracy derives from price-derived variables’ strong correlation with the target. Cross-validation confirms robustness and generalization. Overall, the framework provides an effective and interpretable tool for wheat price forecasting, though the short data collection period and single-product focus limit generalizability. Full article

Shale gas “sweet spot” prediction serves as a pivotal technical link in shale gas exploration and development, directly governing the efficiency of exploration deployment and the economic viability of development projects. To address the research gap in sweet spot prediction for complex synclinal structures, this study establishes an integrated geology–engineering–economics evaluation framework, incorporating artificial intelligence (AI)-assisted parameter optimization and dynamic weight adjustment. This innovative approach overcomes the inherent limitations of single-parameter and static evaluation methods commonly employed in new exploration areas. Focusing on the Upper Ordovician Wufeng Formation to Lower Silurian Longmaxi Formation shale sequences within the Anchang Syncline of northern Guizhou, a comprehensive geological characterization of shale reservoirs was accomplished through the fine processing of 3D seismic data (dominant frequency: 30 Hz; signal-to-noise ratio: 8.5) and statistical analysis of logging data. Prestack elastic parameter inversion technology was utilized to quantitatively predict key geological sweet spot parameters, including the total organic carbon (TOC) content and total gas content, with model validation conducted using core test data. Coupled with prestack and poststack seismic attribute analysis, engineering sweet spot evaluation indicators—encompassing fracture development, in situ stress, the pressure coefficient, and the brittleness index—were established with well-defined quantitative criteria. By integrating multi-source data from geology, geophysics, and engineering dynamics, a three-dimensional evaluation system encompassing “preservation conditions–reservoir quality–engineering feasibility” was constructed, with the random forest algorithm employed for sensitive parameter screening. Research findings indicate that high-quality shale in the study area exhibits a thickness ranging from 17 to 22 m, characterized by a TOC content ≥ 4%, gas content of 4.3–4.8 m³/t, effective porosity of 3.5–5.25%, and brittleness index of 55–75. These properties collectively manifest the “high organic matter enrichment, high gas content, and high brittleness” characteristics. Through multi-parameter weighted comprehensive evaluation using the Analytic Hierarchy Process (AHP), complemented by sensitivity testing, sweet spots were classified into three grades: Class I (63 km²), Class II (31 km²), and Class III (27 km²). An optimized well placement scheme for the southern region was proposed, taking into account long-term production dynamics and economic assessment. This study establishes a multi-parameter, multi-technology integrated sweet spot evaluation system with strong transferability, providing a robust scientific basis for the large-scale exploration and development of shale gas in northern Guizhou and analogous complex structural regions worldwide. Full article

To accurately characterize the complex coupling and nonlinear interactions between meteorological and oceanic variables in offshore wind power scenarios, this study proposes a novel forecasting model based on a “multi-scale fusion-decomposition-reconstruction-optimization-prediction” framework. This model integrates Variational Modal Decomposition (VMD) with the feature-interaction Informer framework, employing an enhanced Honey Badger Algorithm (HBA) for the collaborative optimization of their key parameters. The enhanced HBA integrates cubic chaotic mapping, random perturbation strategy, elite tangent search, and differential mutation operations to strengthen its global optimization capability and convergence efficiency. The model construction process proceeds as follows: First, sample entropy (SE) is applied to evaluate the entropy values and reconstruct sequences of the modal components obtained from VMD. Subsequently, the dynamic adjustment of the maximum information coefficient (DE-MIC) is employed to select key input variables from multi-source features. Subsequently, the feature interaction-probabilistic sparse attention mechanism (FI-ProbSparse-AM) unique to the feature interaction-based Informer is employed to construct an attention architecture capable of explicitly modeling dependencies among multidimensional variables, thereby effectively capturing the spatiotemporal latent correlations between wind power output and multi-source features. Experiments based on real offshore wind farm data demonstrate that the MAPE values are reduced by approximately 11% compared to existing benchmark models. The proposed method demonstrates significant advantages in both prediction accuracy and stability. Full article

Objectives: Radiomics has enhanced quantitative ultrasound (QUS) imaging based on envelope statistics for liver fibrosis evaluation. However, early detection of liver fibrosis in patients with hepatic steatosis remains challenging. This study is to develop ultrasound scatteromics prediction models, utilizing simplified feature sets from multimodal QUS envelope statistics imaging, for detecting early-stage liver fibrosis (stage ≥ F1) and significant fibrosis (≥F2) in the presence of hepatic steatosis. Methods: The dataset in this prospective study included 252 subjects (n = 125 for training and validation; n = 127 subjects for independent testing), which underwent blood tests, liver biopsy, and ultrasound radiofrequency data acquisition. In scatteromics analysis, multimodal QUS envelope statistics imaging (Nakagami, homodyned K, and information entropy statistics) was employed. For each imaging, a predefined simplified feature set was calculated, followed by feature selection for machine learning using support vector machine (SVM), random forest (RF), and linear discriminant analysis (LDA). The scatteromics model was obtained using a repeated five-fold stratified cross-validation and then independently tested. The performance was evaluated by the area under the receiver operating characteristic curve (AUROC); scatteromics features were also compared with aspartate aminotransferase (AST) and alanine aminotransferase (ALT). Results: Scatteromics features showed no significant correlation with AST and ALT, with correlation coefficients ranging from 0.003 to 0.28. In patients with coexisting hepatic steatosis, scatteromics significantly outperformed QUS envelope statistics imaging in identifying early-stage liver fibrosis, achieving AUROC values of 0.85 to 0.87 for the training and validation datasets, and 0.78 to 0.81 for the testing dataset. In comparison, scatteromics demonstrated modest performance in detecting significant liver fibrosis (≥F2), with AUROC ranging from 0.66 to 0.71 in the training cohort and 0.64 to 0.76 in the testing cohort. Conclusions: The proposed scatteromics model streamlines the data analysis workflow of conventional QUS radiomics, enabling early detection of liver fibrosis with reduced dependence on inflammation and hepatic steatosis. Full article

Decarbonizing the transport sector is crucial for achieving global carbon peaking and carbon neutrality goals. Electric taxis (e-taxis), which play a vital role in urban public transportation, are central to this transition. However, their operational performance deteriorates significantly under extremely cold conditions. Existing planning models for charging infrastructure often overlook the impact of low temperatures, creating a critical research gap. To address this issue, we propose a novel planning framework using Urumqi, China (43.8° N, 87.6° E) as a case study. Urumqi is a major cold-region metropolis, where January temperatures regularly drop below $-20$ °C. Our methodology includes two key steps: integrating 412 driver questionnaires and 1.2 million high-resolution GPS trajectories to extract temperature-sensitive charging demand profiles; and incorporating these profiles into an integer linear programming (ILP) model to minimize lifecycle costs, considering climatic constraints, taxi operation patterns, and grid limitations. A key innovation is a temperature-correction coefficient, which dynamically adjusts vehicle energy consumption and driving range based on ambient temperature. Results show superiority over conventional (temperature-ignoring) and random plans: 14-fold lower annualized cost, 23-fold shorter average queuing time, 96.2% high-frequency demand coverage (+16.6%), and 78% charging station utilization (+50.0%). It achieves 29.8–32.3% cost savings at $-5$ °C (over 25.9% even at $-35$ °C) and scales stably for 5–50% e-taxi penetration, offering a transferable framework for cold-region e-taxi charging optimization. Full article

The dry sliding wear behaviour of nanoclay-filled bio-based epoxy composites was systematically investigated using a Taguchi L16 experimental design by varying nanoclay content (0–0.35 wt.%), normal load, sliding speed, and sliding time against an EN24 steel counterface. Wear loss, specific wear rate (SWR), frictional response, thermal rise, and energy-based descriptors were quantified, followed by mathematical and machine-learning (ML) based modelling. The results demonstrate that nanoclay addition significantly improves tribological performance up to an optimal content of 0.25 wt.%, beyond which wear instability increases. Compared with neat epoxy, the 0.25 wt.% nanoclay composite exhibited a reduction in steady-state coefficient of friction from ~0.53 to ~0.42, along with a 25–30% decrease in specific wear rate and the lowest energy-to-wear conversion efficiency, indicating more effective utilization of frictional energy. Taguchi analysis identified normal load as the dominant factor governing wear variation (~68% contribution), followed by sliding speed (~17%), while nanoclay content contributed ~5%. An energy-based wear model showed improved correlation with experimental wear volume (R² ≈ 0.93) compared to a classical Archard-type formulation. ML prediction using a random forest model with leave-one-out cross-validation achieved an R² ≈ 0.64 for SWR. Scanning electron microscopy (SEM) and atomic force microscopy (AFM) analyses confirmed a transition from severe abrasive wear in neat epoxy to stable tribofilm formation at 0.25 wt.% nanoclay, followed by heterogeneous debris-mediated wear at higher filler content. The observed reduction in wear loss and frictional energy dissipation supports sustainable materials innovation aligned with SDG 9 (Industry, Innovation and Infrastructure) and SDG 12 (Responsible Consumption and Production), while improved operational efficiency is consistent with SDG 7 (Affordable and Clean Energy). Full article

In modern survey sampling, particularly when using stratified random sampling (StRS), the existence of outliers and model mis-specifications is a daunting challenge to the conventional parametric and nonparametric methods of estimating parameters. This research presents a new type of predictive estimator that is synergistic to both robust regression and nonparametric local polynomial kernel regression. It aims to offer more resistant and efficient estimators of the average parameter in the areas where supplementary information is known, but irregularity in the data is usual. The proposed estimators use dual calibration methods based on both auxiliary variable means and coefficients of variation, which improves efficiency. This framework enhances predictive performance by integrating the adaptability of kernel-based smoothing with the outlier resistance of robust regression. The accuracy of the suggested estimators is measured by using large scales of simulation experiments on artificial populations with structural heterogeneity and outlier contamination. An empirical comparison, based on percentage relative efficiency (PRE), indicates that the new estimators are superior to classical methods based on the use of a kernel regression in most bandwidth selection strategies. In addition to bringing methodological innovation as it connects distribution theory, regression models, and robust estimation strategies, this work also offers the usefulness of survey practitioners who work with complicated and imperfect real-life data of fisheries and radiations. Full article

The cultivation of potatoes is essential for rural food security, and the use of Unmanned Aerial Vehicle Red-Green-Blue (UAV-RGB) imagery allows for precise and cost-effective estimation of yield and identification of varieties, overcoming the limitations of manual assessment. We evaluated four INIA varieties (Bicentenario, Canchán, Shulay and Tahuaqueña) by integrating agronomic measurements (height, number and weight of tubers, leaf health) with color and textural indices derived from RGB orthomosaics. Yield prediction was modeled using Random Forest (RF) and Gradient Boosting (GB); varietal identification was approached with (i) a Convolutional Neural Network (CNN) that classifies RGB images and (ii) classical models such as Random Forest, Support Vector Machines (SVMs), K-Nearest Neighbors (KNNs), Decision Trees and Logistic Regression trained on EfficientNetB0 embeddings. The results showed significant genotypic differences in yield (p < 0.001): Tahuaqueña 13.86 ± 0.27 t ha⁻¹ and Bicentenario 6.65 ± 0.27 t ha⁻¹. The number of tubers (r = 0.52) and plant height (r = 0.23) correlated with yield; RGB indices showed low correlations (r < 0.3) and high redundancy (r > 0.9). RF achieved a better fit (Coefficient of determination, R² = 0.54; Root Mean Square Error, RMSE = 2.72 t ha⁻¹), excelling in stolon development (R² = 0.66) and losing precision in maturation due to foliar senescence. In classification, the CNN and RF on embeddings achieved F1-macro ≈ 0.69 and 0.66 (Receiver Operating Characteristic—Area Under the Curve, ROC AUC RF = 0.89), with better identification of Bicentenario and Shulay. We conclude that UAV-RGB is a cost-effective alternative for phenotypic monitoring and varietal selection in high Andean contexts. These findings support the integration of UAV-RGB imagery into breeding and monitoring pipelines in resource-limited Andean systems. Full article