Search Results (648)

This study evaluates two approaches for detecting solar photovoltaic (PV) installations across agricultural areas, emphasizing their role in supporting sustainable energy monitoring, land management, and planning. Accurate PV mapping is essential for tracking renewable energy deployment, guiding infrastructure development, assessing land-use impacts, and informing policy decisions aimed at reducing carbon emissions and fostering climate resilience. The first approach applies deep learning-based semantic segmentation to high-resolution RGB orthophotos, using the pretrained “Solar PV Segmentation” model, which achieves an F1-score of 95.27% and an IoU of 91.04%, providing highly reliable PV identification. The second approach employs multitemporal pixel-wise spectral classification using Sentinel-2 imagery, where the best-performing neural network achieved a precision of 99.22%, a recall of 96.69%, and an overall accuracy of 98.22%. Both approaches coincided in detecting 86.67% of the identified parcels, with an average surface difference of less than 6.5 hectares per parcel. The Sentinel-2 method leverages its multispectral bands and frequent revisit rate, enabling timely detection of new or evolving installations. The proposed methodology supports the sustainable management of land resources by enabling automated, scalable, and cost-effective monitoring of solar infrastructures using open-access satellite data. This contributes directly to the goals of climate action and sustainable land-use planning and provides a replicable framework for assessing human-induced changes in land cover at regional and national scales. Full article

Accurate and timely 3D vegetation structure information is essential for ecological modeling and land management. However, these needs often cannot be met with existing airborne LiDAR surveys, whose broad-area coverage comes with trade-offs in point density and update frequency. To address these limitations, this study introduces a deep learning framework built on attention mechanisms, the fundamental building block of modern large language models. The framework upsamples sparse (<22 pt/m²) airborne LiDAR point clouds by fusing them with stacks of multi-temporal optical (NAIP) and L-band quad-polarized Synthetic Aperture Radar (UAVSAR) imagery. Utilizing a novel Local–Global Point Attention Block (LG-PAB), our model directly enhances 3D point-cloud density and accuracy in vegetated landscapes by learning structure directly from the point cloud itself. Results in fire-prone Southern California foothill and montane ecosystems demonstrate that fusing both optical and radar imagery reduces reconstruction error (measured by Chamfer distance) compared to using LiDAR alone or with a single image modality. Notably, the fused model substantially mitigates errors arising from vegetation changes over time, particularly in areas of canopy loss, thereby increasing the utility of historical LiDAR archives. This research presents a novel approach for direct 3D point-cloud enhancement, moving beyond traditional raster-based methods and offering a pathway to more accurate and up-to-date vegetation structure assessments. Full article

Object-Based Image Analysis (OBIA) generates high-dimensional features that frequently induce the curse of dimensionality, impairing classification efficiency and generalizability in high-resolution remote sensing images. To address these challenges while simultaneously overcoming the limitations of single-criterion feature selection and enhancing temporal adaptability, we propose a novel feature selection framework named Mutual information Pre-filtering and Genetic-Hill climbing hybrid Feature Selection (MPGH-FS), which integrates Mutual Information Correlation Coefficient (MICC) pre-filtering, Genetic Algorithm (GA) global search, and Hill Climbing (HC) local optimization. Experiments based on multi-temporal GF-2 imagery from 2018 to 2023 demonstrated that MPGH-FS could reduce the feature dimension from 232 to 9, and it achieved the highest Overall Accuracy (OA) of 85.55% and a Kappa coefficient of 0.75 in full-scene classification, with training and inference times limited to 6 s and 1 min, respectively. Cross-temporal transfer experiments further validated the method’s robustness to inter-annual variation within the same area, with classification accuracy fluctuations remaining below 4% across different years, outperforming comparative methods. These results confirm that MPGH-FS offers significant advantages in feature compression, classification performance, and temporal adaptability, providing a robust technical foundation for efficient and accurate multi-temporal remote sensing classification. Full article

This study explores the transformative potential of cyber technologies in the preservation, representation, and restoration of architectural heritage. Bridging technical and humanistic dimensions, it examines how tools like Heritage Building Information Modeling (HBIM), As-Designed BIM, and Virtual Reality (VR) support deeper, multilevel, and multitemporal understandings of cultural sites. Central to the research is an experimental restoration project on the castles of Civitella in Val di Chiana (Arezzo), serving as a methodological testbed for a digitally integrated approach. Developed through a scan-to-BIM process, the project yields a high-fidelity immersive ecosystem—both a rigorous model for future restoration and a VR platform enabling access to previously unreachable spaces. Here, representation is not a secondary or illustrative phase but a central, operative component in historical interpretation and architectural design. This approach embraces cyber representation: a digitally mediated, interactive, and evolving form that extends heritage beyond its physical boundaries. The immersive model fosters renewed dialogue between past and present, encouraging critical reflection on material authenticity, spatial transformation, and conservation strategies within a dynamic, participatory, interactive webVR environment. Representation thus becomes a generative and narrative tool, shaping restoration scenarios while enhancing analytical depth and public engagement. The study ultimately proposes a shift in historical storytelling toward a polyphonic, experiential, cyber-mediated narrative—where technology, memory, and perception converge to create new forms of cultural continuity. Full article

Hydrological runoff prediction serves as the core technological foundation for water resource management and flood/drought mitigation. However, the nonlinear, non-stationary, and multi-temporal scale characteristics of runoff data result in insufficient accuracy of traditional prediction methods. To address the challenges of single decomposition methods’ inability to effectively separate multi-scale components and single deep learning models’ limitations in capturing long-range dependencies or extracting local features, this study proposes an Informer-GRU runoff prediction model based on STL-CEEMDAN secondary decomposition and Gorilla Troops Optimizer (GTO). The model extracts trend, seasonal, and residual components through STL decomposition, then performs fine decomposition of the residual components using CEEMDAN to achieve effective separation of multi-scale features. By combining Informer’s ProbSparse attention mechanism with GRU’s temporal memory capability, the model captures both global dependencies and local features. GTO is introduced to optimize model architecture and training hyperparameters, while a multi-objective loss function is designed to ensure the physical reasonableness of predictions. Using daily runoff data from the Liyuan Basin in Yunnan Province (2015–2023) as a case study, the results show that the model achieves a coefficient of determination (R²) and Nash-Sutcliffe efficiency coefficient (NSE) of 0.9469 on the test set, with a Kling-Gupta efficiency coefficient (KGE) of 0.9582, significantly outperforming comparison models such as LSTM, GRU, and Transformer. Ablation experiments demonstrate that components such as STL-CEEMDAN secondary decomposition and GTO optimization enhance model performance by 31.72% compared to the baseline. SHAP analysis reveals that seasonal components and local precipitation station data are the core driving factors for prediction. This study demonstrates exceptional performance in practical applications within the Liyuan Basin, providing valuable insights for water resource management and prediction research in this region. Full article

This research presents a comprehensive spatiotemporal assessment of the effects of climate change and anthropogenic pressures on the water surface area and quality of the Sidi Salem Dam, the largest reservoir in Northern Tunisia. Located within a sub-humid to Mediterranean humid bioclimatic zone, the dam plays a vital role in regional water supply, irrigation, and flood control. Utilizing a 40-year dataset (1985–2025), this study integrates multi-temporal satellite imagery and geospatial analysis using Geographic Information System (GIS) and remote sensing (RS) techniques. The temporal variability of the dam’s surface water extent was monitored through indices such as the Normalized Difference Water Index (NDWI). The analysis was further supported by climate data, including records of precipitation, temperature, and evapotranspiration, to assess correlations with observed hydrological changes. The findings revealed a significant reduction in the dam’s surface area, from approximately 37.8 km² in 1985 to 19.8 km² in 2025, indicating a net loss of 18 km² (47.6%). The Mann–Kendall trend test confirmed a significant long-term increase in annual precipitation, while annual temperature showed no significant trend. Nevertheless, recent observations indicate a decline in precipitation during the most recent period. Furthermore, Pearson correlation analysis revealed a significant negative relationship between precipitation and temperature, suggesting that wet years are generally associated with cooler conditions, whereas dry years coincide with warmer conditions. This hydroclimatic interplay underscores the complex dynamics driving reservoir fluctuations. Simultaneously, land use changes in the catchment area, particularly the expansion of agriculture, urban development, and deforestation have led to increased surface runoff and soil erosion, intensifying sediment deposition in the reservoir. This has progressively reduced the dam’s storage capacity, further diminishing its water storage efficiency. This study also investigates the degradation of water quality associated with declining water levels and climatic stress. Indicators such as turbidity and salinity were evaluated, showing clear signs of deterioration resulting from both natural and human-induced processes. Increased salinity and pollutant concentrations are primarily linked to reduced dilution capacity, intensified evaporation, and agrochemical runoff containing fertilizers and other contaminants. Full article

As electric grids decarbonize and distributed energy resources (DERs) become increasingly prevalent, interconnection assessments must evolve to reflect operational variability and control flexibility. This paper highlights key modeling limitations observed in practice and reviews approaches for modeling uncertainty. It then introduces a Probabilistic Deliverability Assessment (PDA) framework designed to complement and extend existing procedures. The framework integrates scenario-based AC optimal power flow (AC OPF), corrective dispatch, and optional multi-temporal constraints. Together, these form a structured methodology for quantifying DER utilization, deliverability, and reliability under uncertainty in load, generation, and topology. Outputs include interpretable metrics with confidence intervals that inform siting decisions and evaluate compliance with reliability thresholds across sampled operating conditions. A case study on Puerto Rico’s publicly available bulk power system model demonstrates the framework’s application using minimal input data, consistent with current interconnection practice. Across staged fossil generation retirements, the PDA identifies high-value DER sites and regions requiring additional reactive power support. Results are presented through mean dispatch signals, reliability metrics, and geospatial visualizations, demonstrating how the framework provides transparent, data-driven siting recommendations. The framework’s modular design supports incremental adoption within existing workflows, encouraging broader use of AC OPF in interconnection and planning contexts. Full article

As fluvial deposition features, river islands originate from persistently exposed sandbars. Their morphological evolution responds to hydrological dynamics, sediment budgets, and human modifications of river systems. This study conducts a quantitative analysis of the spatiotemporal evolution of four river islands in China’s Yangtze River Estuary (YRE), utilizing multitemporal Landsat imagery (MSS, TM, ETM+, and OLI) at five-year intervals from 1974 to 2024. This analysis employed thresholding, binarization, image registration, cropping, and cluster analysis. Hydrological data (runoff and sediment flux) from Datong Station were concurrently evaluated to explore the driving factors of evolution. The findings suggested the following: (1) MSS/TM/ETM+/OLI images were effective for accurately extracting river island information, and the results were consistent with the accuracy verification. (2) The cumulative area and growth rate of the river islands have exhibited an upward trend over time, with Jiuduansha growing the fastest. (3) Runoff and sediment discharge are the primary natural controls on morphological evolution, with a weak positive correlation (R = 0.293) and a strong negative correlation (R = −0.915) with the area of river islands, respectively. Anthropogenic drivers such as land reclamation, sediment enhancement projects, and the Three Gorges Dam are equally critical. Full article

Multi-temporal remote sensing image matching plays a crucial role in tasks such as detecting changes in urban buildings, monitoring agriculture, and assessing ecological dynamics. Due to temporal variations in images, significant changes in land features can lead to low accuracy or even failure when matching results. To address these challenges, in this study, a remote sensing image matching framework is proposed based on multi-perception and enhanced feature description. Specifically, the framework consists of two core components: a feature extraction network that integrates multiple perceptions and a feature descriptor enhancement module. The designed feature extraction network effectively focuses on key regions while leveraging depthwise separable convolutions to capture local features at different scales, thereby improving the detection capabilities of feature points. Furthermore, the feature descriptor enhancement module optimizes feature point descriptors through self-enhancement and cross-enhancement phases. The enhanced descriptors not only extract the geometric information of the feature points but also integrate global contextual information. Experimental results demonstrate that, compared to existing remote sensing image matching methods, our approach maintains a strong matching performance under conditions of angular and scale variation. Full article

To tackle the challenges posed by substantial variations in target scale, intricate background interference, and the likelihood of missing small targets in multi-temporal UAV maize tassel imagery, an optimized lightweight detection model derived from YOLOv11 is introduced, named OTB-YOLO. Here, “OTB” is an acronym derived from the initials of the model’s core improved modules: Omni-dimensional dynamic convolution (ODConv), Triplet Attention, and Bi-directional Feature Pyramid Network (BiFPN). This model integrates the PaddlePaddle open-source maize tassel recognition benchmark dataset with the public Multi-Temporal Drone Corn Dataset (MTDC). Traditional convolutional layers are substituted with omni-dimensional dynamic convolution (ODConv) to mitigate computational redundancy. A triplet attention module is incorporated to refine feature extraction within the backbone network, while a bidirectional feature pyramid network (BiFPN) is engineered to enhance accuracy via multi-level feature pyramids and bidirectional information flow. Empirical analysis demonstrates that the enhanced model achieves a precision of 95.6%, recall of 92.1%, and mAP@0.5 of 96.6%, marking improvements of 3.2%, 2.5%, and 3.1%, respectively, over the baseline model. Concurrently, the model’s computational complexity is reduced to 6.0 GFLOPs, rendering it appropriate for deployment on UAV edge computing platforms. Full article

Global food security is increasingly challenged by climate change and the availability of arable land. This situation calls for improved crop monitoring and management strategies. Rice is a staple food for nearly half of the world’s population and a significant source of calories. Accurately identifying rice varieties is crucial for maintaining varietal purity, planning agricultural activities, and enhancing genetic improvement strategies. This study evaluates the effectiveness of machine learning algorithms to identify the most effective approach to predicting rice varieties, using multitemporal Sentinel-2 images in the Marismas del Guadalquivir of Sevilla, Spain. Spectral reflectance data were collected from ten Sentinel-2 bands, which include visible, red-edge, near-infrared, and shortwave infrared regions, at two key phenological stages: tillering and reproduction. The models were trained on pixel-level data from the growing seasons of 2021 and 2024, and they were evaluated using a test set from 2022. Four classifiers were compared: random forest, XGBoost, K-nearest neighbors, and logistic regression. Performance was assessed based on accuracy, precision, recall, specificity and F1 score. Non-linear models outperformed linear ones. The highest performance was achieved with the Random Forest classifier during the reproduction phase, reaching an exceptional accuracy of 0.94 using all bands or only the most informative subset (red edge, NIR, and SWIR). This classifier also maintained excellent accuracy (0.93 and 0.92) during the initial tillering phase. This fact demonstrates that it is possible to perform reliable varietal mapping in the early stages of the growing season. Full article

Change detection technology holds significant importance in disciplines such as urban planning, land utilization tracking, and hazard evaluation, as it can efficiently and accurately reveal dynamic regional change processes, providing crucial support for scientific decision-making and refined management. Although deep learning methods based on computer vision have achieved remarkable progress in change detection, they still face challenges including reducing dynamic background interference, capturing subtle changes, and effectively fusing multi-temporal data features. To address these issues, this paper proposes a novel change detection model called OFNet. Building upon existing Siamese network architectures, we introduce an optical flow branch module that supplements pixel-level dynamic information. By incorporating motion features to guide the network’s attention to potential change regions, we enhance the model’s ability to characterize and discriminate genuine changes in cross-temporal remote sensing images. Additionally, we innovatively propose a dual-domain attention mechanism that simultaneously models discriminative features in both spatial and frequency domains for change detection tasks. The spatial attention focuses on capturing edge and structural changes, while the frequency-domain attention strengthens responses to key frequency components. The synergistic fusion of these two attention mechanisms effectively improves the model’s sensitivity to detailed changes and enhances the overall robustness of detection. Experimental results demonstrate that OFNet achieves an IoU of 83.03 on the LEVIR-CD dataset and 82.86 on the WHU-CD dataset, outperforming current mainstream approaches and validating its superior detection performance and generalization capability. This presents a novel technical method for environmental observation and urban transformation analysis tasks. Full article

Urban heat exposure has become an increasingly critical environmental issue under the dual pressures of global climate warming and rapid urbanization, posing significant threats to public health and urban sustainability. However, conventional linear regression models often fail to capture the complex, nonlinear interactions among multiple environmental factors, and studies confined to single LCZ types lack a comprehensive understanding of urban thermal mechanisms. This study takes the central urban area of Zhengzhou as a case and proposes an integrated “Local Climate Zone (LCZ) framework + random forest-based multi-factor contribution analysis” approach. By incorporating multi-temporal Landsat imagery, this method effectively identifies nonlinear drivers of heat exposure across different urban morphological units. Compared to traditional approaches, the proposed model retains spatial heterogeneity while uncovering intricate regulatory pathways among contributing factors, demonstrating superior adaptability and explanatory power. Results indicate that (1) high-density built-up zones (LCZ1 and E) constitute the core of heat exposure, with land surface temperatures (LSTs) 6–12 °C higher than those of natural surfaces and LCZ3 reaching a peak LST of 49.15 °C during extreme heat events; (2) NDVI plays a dominant cooling role, contributing 50.5% to LST mitigation in LCZ3, with the expansion of low-NDVI areas significantly enhancing cooling potential (up to 185.39 °C·km²); (3) LCZ5 exhibits an anomalous spatial pattern with low-temperature patches embedded within high-temperature surroundings, reflecting the nonlinear impacts of urban form and anthropogenic heat sources. The findings demonstrate that the LCZ framework, combined with random forest modeling, effectively overcomes the limitations of traditional linear models, offering a robust analytical tool for decoding urban heat exposure mechanisms and informing targeted climate adaptation strategies. Full article

Soil fertility is the essential attribute of soil quality. Large-scale coal mining has led to the continuous deterioration of the fragile ecosystems in arid and semi-arid mining areas. As one of the key indicators for land ecological restoration in these coal mining regions, rapidly and accurately monitoring topsoil fertility and its spatial variation information holds significant importance for ecological restoration evaluation. This study takes Wuhai City in the Inner Mongolia Autonomous Region of China as a case study. It establishes and evaluates various soil indicator inversion models using multi-temporal Landsat8 OLI multispectral imagery and measured soil sample nutrient content data. The research constructs a comprehensive evaluation method for surface soil fertility based on multispectral remote sensing monitoring and achieves spatiotemporal variation analysis of soil fertility characteristics. The results show that: (1) The 6SV (Second Simulation of the Satellite Signal in the Solar Spectrum Vector version)-SVM (Support Vector Machine) prediction model for surface soil indicators based on Landsat8 OLI imagery achieved prediction accuracy with R² values above 0.85 for all six soil nutrient contents in the study area, thereby establishing for the first time a rapid assessment method for comprehensive topsoil fertility using multispectral remote sensing monitoring. (2) Long-term spatiotemporal evaluation of soil indicators was achieved: From 2015 to 2025, the spatial distribution of soil indicators showed certain variability, with soil organic matter, total phosphorus, available phosphorus, and available potassium contents demonstrating varying degrees of increase within different ranges, though the increases were generally modest. (3) Long-term spatiotemporal evaluation of comprehensive soil fertility was accomplished: Over the 10 years, Grade IV remained the dominant soil fertility level in the study area, accounting for about 32% of the total area. While the overall soil fertility level showed an increasing trend, the differences in soil fertility levels decreased, indicating a trend toward homogenization. Full article

Comprehensive, standardised, multi-temporal inventories of rainfall-induced landslides linked to soil moisture remain scarce, especially in tropical regions. Addressing this gap, we present a multi-source urban inventory for Brazil’s Baixada Santista region (1988–2024). A key advance is the introduction of geographical and temporal confidence classifications, which indicates precisely how each landslide’s location and occurrence date are known, thereby addressing a previously overlooked criterion in Brazil’s landslide data treatment. The inventory comprises 2534 records categorised by spatial (G1–G3) and temporal (T1–T3) confidence. Notable findings include the following: (i) confidence classifications enhance inventory reliability for research and early warning, though precise temporal data remains challenging; (ii) multi-source integration with UAV validation is key to robust inventories in urban tropical regions; (iii) soil moisture complements rainfall-based warnings, but requires local calibration for satellite-derived estimates; (iv) data gaps and biases underscore the need for standardised landslide documentation; and (v) the framework is transferable, providing a scalable model for Brazil and worldwide. Despite limitations, the inventory provides a foundation for (i) susceptibility and hazard modelling; (ii) empirical thresholds for early warning; and (iii) climate-related trend analyses. Overall, the framework offers a sustainable, practical, transferable method for worldwide and contributes to strengthening disaster information systems and early warning capacities. Full article