Search Results (1,185)

Understanding household vehicle ownership dynamics in the post-COVID-19 era is critical for designing equitable, resilient, and sustainable transportation policies. This study employs an interpretable machine learning framework to model household vehicle ownership using data from the 2022 National Household Travel Survey (NHTS)—the first nationally representative U.S. dataset collected after the onset of the pandemic. A binary classification task distinguishes between single- and multi-vehicle households, applying an ensemble of algorithms, including Random Forest, XGBoost, Support Vector Machines (SVM), and Naïve Bayes. The Random Forest model achieved the highest predictive accuracy (86.9%). To address the interpretability limitations of conventional machine learning approaches, SHapley Additive exPlanations (SHAP) were applied to extract global feature importance and directionality. Results indicate that the number of drivers, household income, and vehicle age are the most influential predictors of multi-vehicle ownership, while contextual factors such as housing tenure, urbanicity, and household lifecycle stage also exert substantial influence highlighting the spatial and demographic heterogeneity in ownership behavior. Policy implications include the design of equity-sensitive strategies such as targeted mobility subsidies, vehicle scrappage incentives, and rural transit innovations. By integrating explainable artificial intelligence into national-scale transportation modeling, this research bridges the gap between predictive accuracy and interpretability, contributing to adaptive mobility strategies aligned with the United Nations Sustainable Development Goals (SDGs), particularly SDG 11 (Sustainable Cities), SDG 10 (Reduced Inequalities), and SDG 13 (Climate Action). Full article

Rice is one of the most important staple crops in China, and the rapid and accurate extraction of rice planting areas plays a crucial role in the agricultural management and food security assessment. However, the existing rice field identification methods faced the significant challenges in mountainous regions due to the severe cloud contamination, insufficient utilization of multi-dimensional features, and limited classification accuracy. This study presented a novel rice field identification method based on the Graph Convolutional Networks (GCN) that effectively integrated multi-source remote sensing data tailored for the complex mountainous terrain. A coarse-to-fine cloud removal strategy was developed by fusing the synthetic aperture radar (SAR) imagery with temporally adjacent optical remote sensing imagery, achieving high cloud removal accuracy, thereby providing reliable and clear optical data for the subsequent rice mapping. A comprehensive multi-feature library comprising spectral, texture, polarization, and terrain attributes was constructed and optimized via a stepwise selection process. Furthermore, the 19 key features were established to enhance the classification performance. The proposed method achieved an overall accuracy of 98.3% for the rice field identification in Huoshan County of the Dabie Mountains, and a 96.8% consistency compared to statistical yearbook data. The ablation experiments demonstrated that incorporating terrain features substantially improved the rice field identification accuracy under the complex topographic conditions. The comparative evaluations against support vector machine (SVM), random forest (RF), and U-Net models confirmed the superiority of the proposed method in terms of accuracy, local performance, terrain adaptability, training sample requirement, and computational cost, and demonstrated its effectiveness and applicability for the high-precision rice field distribution mapping in mountainous environments. Full article

Heritage Building Information Modelling (HBIM) requires the accurate classification of diverse building elements from 3D point clouds. This study presents a novel classification approach integrating a bespoke Uniclass-derived taxonomy with a hierarchical Random Forest model. It was applied to the 17th-century Queen’s House in Greenwich, a building rich in classical architectural elements whose geometric properties are often defined by principles of symmetry. The bespoke classification was implemented across three levels (50 mm, 20 mm, 5 mm point cloud resolutions) and evaluated against the prior experiment that used Uniclass classification. Results showed a substantial improvement in classification precision and overall accuracy at all levels. The Level 1 classifier’s accuracy increased by 15% of points (relative ~50% improvement) with the bespoke classification taxonomy, reducing the misclassifications and error propagation in subsequent levels. This research demonstrates that tailoring the Uniclass building classification for heritage-specific geometry significantly enhances machine learning performance, which, to date, has not been published in the academic domain. The findings underscore the importance of adaptive taxonomies and suggest pathways for integrating multi-scale features and advanced learning methods to support automated HBIM workflows. Full article

Land degradation in Iraq’s Mesopotamian plain threatens food security and rural livelihoods, yet the relative roles of climatic water deficits versus anthropogenic pressures remain poorly attributed in space. We test the hypothesis that multi-timescale climatic water deficits (SPEI-03/-06/-12) exert a stronger effect on vegetation degradation risk than anthropogenic pressures, conditional on hydrological connectivity and irrigation. Using Babil and Al-Qadisiyah (2000–2023) as a case, we implement a four-part pipeline: (i) Fractional Vegetation Cover with Mann–Kendall/Sen’s slope to quantify greening/browning trends; (ii) LandTrendr to extract disturbance timing and magnitude; (iii) annual LULC maps from a Random Forest classifier to resolve transitions; and (iv) an XGBoost classifier to map degradation risk and attribute climate vs. anthropogenic influence via drop-group permutation (ΔAUC), grouped SHAP shares, and leave-group-out ablation, all under spatial block cross-validation. Driver attribution shows mid-term and short-term drought (SPEI-06, SPEI-03) as the strongest predictors, and conditional permutation yields a larger average AUC loss for the climate block than for the anthropogenic block, while grouped SHAP shares are comparable between the two, and ablation suggests a neutral to weak anthropogenic edge. The XGBoost model attains AUC = 0.884 (test) and maps 9.7% of the area as high risk (>0.70), concentrated away from perennial water bodies. Over 2000–2023, LULC change indicates CA +515 km², HO +129 km², UL +70 km², BL −697 km², WB −16.7 km². Trend analysis shows recovery across 51.5% of the landscape (+29.6% dec⁻¹ median) and severe decline over 2.5% (−22.0% dec⁻¹). The integrated design couples trend mapping with driver attribution, clarifying how compounded climatic stress and intensive land use shape contemporary desertification risk and providing spatial priorities for restoration and adaptive water management. Full article

Accurate and robust power quality disturbance (PQD) classification is critical for modern electrical grids, particularly in noisy environments. This study presents a comprehensive comparative evaluation of machine learning (ML) and deep learning (DL) models for automatic PQD identification. The models evaluated include Support Vector Machines (SVM), Decision Trees (DT), Random Forest (RF), k-Nearest Neighbors (kNN), Gradient Boosting (GB), and Dense Neural Networks (DNN). For experimentation, a hybrid dataset, comprising both synthetic and real signals, was used to assess model performance. The robustness of the models was evaluated by systematically introducing Gaussian noise across a wide range of Signal-to-Noise Ratios (SNRs). A central objective was to directly benchmark the practical implementation and performance of these models across two widely used platforms: MATLAB R2024a and Python 3.11. Results show that ML models achieve high accuracies, exceeding $95\%$ at an SNR of 10 dB. DL models exhibited remarkable stability, maintaining $97\%$ accuracy for SNRs above 10 dB. However, their performance degraded significantly at lower SNRs, revealing specific confusion patterns. The analysis underscores the importance of multi-domain feature extraction and adaptive preprocessing for achieving resilient PQD classification. This research provides valuable insights and a practical guide for implementing and optimizing robust PQD classification systems in real-world, noisy scenarios. Full article

In the context of the new power system, high-current switchgear is prone to various faults due to complex operation environments and severe load fluctuations. Among them, an abnormal temperature rise can lead to contact oxidation, insulation aging, and even equipment failure, posing a serious threat to the safety of the distribution system. The operation risk assessment of high-current switchgear has thus become a key to ensuring the safety of the distribution system. Ensemble learning, which integrates the advantages of multiple models, provides an effective approach for accurate and intelligent risk assessment. However, existing ensemble learning methods have shortcomings in feature extraction, time-series modeling, and generalization ability. Therefore, this paper first preprocesses and reduces the dimensionality of multi-source data, such as historical load and equipment operation status. Secondly, we propose an operation risk assessment method for high-current switchgear based on ensemble learning: in the first layer, an improved random forest (RF) is used to optimize feature extraction; in the second layer, an improved long short-term memory (LSTM) network with an attention mechanism is adopted to capture time-series dependent features; in the third layer, an adaptive back propagation neural network (ABPNN) model fused with an adaptive genetic algorithm is utilized to correct the previous results, improving the stability of the assessment. Simulation results show that in temperature rise prediction, the proposed algorithm significantly improves the goodness-of-fit indicator with increases of 15.4%, 4.9%, and 24.8% compared to three baseline algorithms, respectively. It can accurately assess the operation risk of switchgear, providing technical support for intelligent equipment operation and maintenance, and safe operation of the system. Full article

Mountain settlements represent culturally rich but environmentally fragile landscapes, shaped by enduring processes of ecological adaptation and human resilience. In western Sichuan, Jiarong Tibetan villages, with their distinctive integration of defensive stone towers and settlements, embody this coupling of culture and the environment. We hypothesize that settlement cores in these villages were shaped by natural environmental factors, with subsequent expansion reinforced by the cultural significance of towers. To test this, we applied a micro-scale spatial–environmental framework to four sample villages in Suopo Township, Danba County. High-resolution World Imagery (Esri, 0.5–1 m, 2022–2023) was classified via a Random Forest algorithm to generate detailed land-use maps, and a 100 × 100 m fishnet grid extracted topographic metrics (elevation, slope, aspect) and accessibility measures (distances to streams, roads, towers). Geographically weighted regression (GWR) was then used to examine how slope, elevation, aspect, proximity to water and roads, and tower distribution affect settlement patterns. The results show built-up density peaks on southeast-facing slopes of 15–30°, at altitudes of 2600–2800 m, and within 50–500 m of streams, co-locating with historic watchtower sites. Based on these findings, we propose four zoning strategies—a Core Protected Zone, a Construction And Development Zone, an Ecological Conservation Zone, and an Industry Development Zone—to balance preservation with growth. The resulting policy recommendations offer actionable guidance for sustaining traditional settlements in complex mountain environments. Full article

With the rapid urban aging trend in China, evaluating the age-friendliness of street environments is critical for inclusive urban planning. This study proposes the Age-Friendly Environment Assessment Tool (AFEAT) to assess street-level age-friendliness in high-density urban contexts, grounded in the World Health Organization’s (WHO) Global Age-Friendly Cities: A Guide and adapted to the spatial characteristics of Nanjing’s Qinhuai District. By integrating multi-source data such as street-view image segmentation, Point of Interest (POI)-based network accessibility, kernel density estimation, Analytic Hierarchy Process (AHP)-derived indicator weights, and Random Forest regression, the study develops a comprehensive and spatialized evaluation framework. The results reveal significant spatial disparities in age-friendliness across street segments, with Safe Mobility, Healthcare Services, and Walkable Environment identified as the most influential factors for older adults. High-performing areas are concentrated in the central urban core, while peripheral zones face challenges such as poor walkability, insufficient lighting, and a lack of facilities. The study recommends strengthening a walkability-based age-friendly safety and healthcare support system and optimizing the spatial distribution of recreational and medical facilities to address mismatches between supply and demand. These findings provide practical guidance for targeted, evidence-based interventions aimed at fostering equitable and resilient urban environments for aging populations. Full article

This study examined the habitat suitability of Kentucky bluegrass (Poa pratensis L.) in Iran’s Fars province, a region characterized by diverse climatic conditions and significant ecological challenges. Utilizing a multi-technique approach that included species distribution models (SDMs) based on machine learning algorithms, geographic information systems (GIS), and remote sensing, we analyzed environmental factors such as climate variables, soil properties, and water availability to understand their influence on habitat suitability. The results indicated that Kentucky bluegrass shows a strong preference for areas near water sources, and its distribution is significantly affected by soil salinity and texture. Among the models tested, Random Forest (RF) and Support Vector Machines (SVMs) demonstrated the highest predictive accuracy. Based on the RF model, the most suitable habitats were identified in the counties of Sepidan, Beyza, Bavanat, Pasargad, and Abadeh. At the same time, areas with lower suitability included Eqlid, Marvdasht, Zarghan, and Arsanjan. Although this study primarily focused on current distribution patterns, the findings provide important insights into the ecological preferences and adaptive capacities of Kentucky bluegrass. These insights are essential for the development of targeted conservation strategies in transitional climate zones. Future studies are recommended to explore the species’ response to future climate scenarios, enhancing its resilience against global climate change. Full article

This study aims to improve the automatic detection of unwanted emails using advanced machine learning and deep learning methods. By reviewing current research over the past five years, a comprehensive combined dataset structure was created containing a total of 81,586 email samples from seven different spam datasets. Class imbalance was addressed through the application of random oversampling and class-weighted loss, and the decision threshold was subsequently tuned for deployment. Among classical machine learning solutions, Random Forest (RF) emerged as the most successful method, while deep learning approaches, such as Transformer-based models like Distilled Bidirectional Encoder Representations from Transformers (DistilBERT) and Robustly Optimized BERT Pretraining Approach (RoBERTa), demonstrated superior performance. The highest test score (99.62%) on a combined static dataset was achieved with a multimodal architecture that combines deep meaningful text representations from DistilBERT with structural text features. Beyond this static performance benchmark, the study investigates the critical challenge of concept drift by performing a temporal analysis on datasets from different eras. The results reveal a significant performance degradation in all models when tested on modern spam, highlighting a critical vulnerability of statically trained systems. Notably, the Transformer-based model demonstrated greater robustness against this temporal decay compared to traditional methods. This study offers not only an effective classification solution but also provides crucial empirical evidence on the necessity of adaptive, continually learning systems for robust spam detection. Full article

Wetland loss and human activities are forcing migratory waterbirds to rely on alternative habitats such as croplands, yet their adaptive habitat use across contrasting landscape contexts remains unclear. The Bar-headed Goose (Anser indicus) is a key indicator species in the wetland ecosystems of the Yunnan–Guizhou Plateau. Comparing differences in its wintering habitat selection and utilization is of great significance for understanding its ecological adaptation mechanisms and formulating regional wetland conservation strategies. In this study, we compared the diurnal habitat use during the wintering period of Bar-headed Geese at three wetlands (Nianhu, Caohai, and Napahai) representing distinct landscape contexts. We used GPS satellite tracking and dynamic Brownian bridge movement modeling, combined with random forest analysis of environmental variables, to quantify diurnal habitat use and selection at each site. Our results revealed significant regional differences in habitat use. In the agriculture-dominated wetlands (Nianhu and Caohai), geese primarily utilized cropland and marsh habitats (Nianhu: cropland 45.88% ± 30.70%, marsh 42.55% ± 33.17%; Caohai: cropland 62.33% ± 12.16%, marsh 28.61% ± 13.62%). In contrast, at Napahai, which is dominated by natural habitats, geese primarily used grassland (65.92% ± 20.01%) and marsh (26.85% ± 21.88%), with minimal use of cropland (4.21% ± 7.00%). Diurnal habitat selection was influenced by multiple environmental factors, with distinct regional differences identified through random forest modeling. In Nianhu, key factors included distance to supplemental feeding site, distance to grassland, distance to woodland, and distance to open water. In Caohai, distance to grassland, distance to nocturnal roost site, distance to settlement, and distance to open water were significant drivers. In Napahai, distance to nocturnal roost site, distance to open water, and distance to marsh were the most influential (all with p < 0.01), reflecting flexible behavioral responses. Based on these findings, we recommend region-specific conservation management strategies. Specifically, supplemental feeding at Nianhu should be strictly regulated. Agricultural planning in farming areas should account for the habitat needs of wintering waterbirds. Grassland and marsh habitats at Napahai should also be more effectively protected. Full article

Accurate forecasting of waste is essential for effective management and allocation of resources. As urban populations grow, the demand for municipal waste systems increases, creating the need for reliable forecasting methods to support planning and decision making. This study compares statistical models Error Trend Seasonality (ETS) and Auto Regressive Integrated Moving Average (ARIMA) with advanced machine learning approaches, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM) networks. Five waste categories were analyzed: dead animal, building, commercial, domestic, and liquid waste. Historical datasets were used for model training and validation, with accuracy assessed through mean absolute error and root mean squared error. Results indicate that ARIMA generally outperforms ETS in forecasting building, commercial, and domestic waste streams, especially in capturing long-term domestic waste patterns. Both statistical models, however, show limitations in predicting liquid waste due to its irregular and highly variable nature, where even baseline models sometimes perform competitively. In contrast, machine learning methods consistently achieve the lowest forecasting errors across all categories. Their capacity to capture nonlinear relationships and adapt to complex datasets highlights their reliability for real-world waste management. The findings underline the importance of selecting forecasting techniques tailored to the characteristics of each waste type rather than applying a uniform method. By improving forecasting accuracy, municipalities and policymakers can design more effective waste management strategies that align with Sustainable Development Goal 11 on sustainable cities and communities, Sustainable Development Goal 12 on responsible consumption and production, and Sustainable Development Goal 13 on climate action. Full article

The Surface Cool Island (SCI) refers to localized reductions in land surface temperature (LST) produced by features that enhance evapotranspiration, shading, and energy flux regulation. In arid urban areas, vegetated parks play a key role in mitigating heat through these mechanisms. This study evaluates how park vegetation structure and spatial configuration influence SCI intensity (ΔTmax) and extent (Lmax) using multi-seasonal, day–night satellite observations in Mexicali, Mexico. A total of 435 parks were analyzed using Landsat 8/9 TIRS (30 m) for LST and Sentinel-2 MSI (10 m) for vegetation mapping via NDVI thresholding and supervised random forest (RF) classification. On average, parks lowered daytime LST by 0.81 °C (max: 6.41 °C), with a mean Lmax of 120 m; nighttime cooling was weaker (avg. ΔTmax: 0.37 °C; Lmax: 48 m). RF-derived metrics explained SCI variability more effectively (R² up to 0.64 for ΔTmax; 0.48 for Lmax) than NDVI-based metrics (R² < 0.35), highlighting the value of object-based land cover classification in capturing vegetation structure. This remote sensing framework offers a scalable method for assessing urban cooling performance and supports climate-adaptive green space design in hot-arid cities. Full article

A significant contradiction exists between the demand for standardized processes and the need for precise process parameter design in the rapid design of superplastic forming (SPF). To address this, an SPF process parameter design method integrating a knowledge graph and artificial intelligence is proposed. Firstly, based on process data analysis, the entity labels, relationship categories, and attributes are determined. On this basis, the knowledge graph for the SPF process is constructed, comprising the pattern layer and the data layer, which provides structured knowledge support for process generation. Secondly, the process parameter prediction model based on small samples and an improved back propagation (BP) neural network is constructed, with model convergence ensured through an adaptive maximum iteration strategy. Experimental results show that the improved BP model significantly outperforms support vector regression (SVR), random forest (RF), extreme gradient boosting (XGBoost), and standard BP models in prediction accuracy. Compared to the standard BP model, the improved model reduces the mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE) by 82.1% (to 0.0005), 46% (to 0.0188), and 57.1% (to 0.0229), respectively. Finally, the effectiveness, feasibility, and superiority of the method in the SPF process parameter design are verified by taking typical hemispherical parts as an example. Full article

Shaded resting zones in rotational grazing systems are prone to thermal stress due to limited ventilation and the congregation of animals during peak heat periods. Addressing these challenges requires sensing solutions that are not only accurate but also capable of adapting to dynamic environmental conditions and energy constraints. In this context, we present the development and simulation-based validation of a self-configurable IoT protocol for adaptive environmental monitoring. The approach integrates embedded machine learning, specifically a Random Forest classifier, to detect critical conditions using synthetic data of temperature, humidity, and CO₂. The model achieved an accuracy of 98%, with a precision of 98%, recall of 85%, and F1-score of 91% in identifying critical states. These results demonstrate the feasibility of embedding adaptive intelligence into IoT-based monitoring solutions. The protocol is conceived as a foundation for integration into physical devices and subsequent evaluation in farm environments such as rotational grazing systems. Full article