Search Results (2,767)

Spatiotemporal change detection of surface cracks in concrete structures is of great importance for evaluating and maintaining their structural health. The development of robotics and 3D computer vision technologies provides new solutions for key subtasks in this process, including automated data acquisition, spatial localization and quantification of cracks, and multi-temporal crack registration. This study proposes an automated UAV- and point cloud-based framework for detecting spatiotemporal changes in cracks in concrete structures. First, the proposed autonomous UAV path-planning algorithm is used to achieve data acquisition that conforms to complex structural geometries. Then, an improved SfM algorithm is employed to realize spatial crack localization and local point cloud densification. Finally, accurate registration of crack point clouds from different periods is achieved based on a two-step registration strategy. Experimental results on a real large-scale concrete structure show that the proposed path-planning algorithm can achieve complete envelope coverage conforming to the structural geometry, with an effective coverage ratio above 99.7%. The dimensional error of structural reconstruction is controlled within 20 mm. The average crack localization time is 4.00 s, and mean absolute error of crack width quantification is 0.44 mm. The average crack registration error is 0.97 mm, thereby enabling accurate tracking of crack evolution. Full article

The increasing frequency and magnitude of glacial lake outburst floods pose a severe threat to the safety of downstream communities. However, Interference from glacier shadows and mountain shading reduces the accuracy of remote sensing-based glacial lake detection. We propose a two-level nested framework that integrates global spatiotemporal aggregation and local adaptive enhancement. At the global level, the 80th temporal percentile (P80) of multi-temporal AWEI imagery is used to construct a stable water-background composite and suppress short-term seasonal noise. Multi-source physical constraints, including the Normalized Difference Snow Index (NDSI), a DEM-derived slope constraint (slope < 10°), and red-band reflectance thresholds (0.3 < BandRed < 1.6), are applied to suppress interference from land, terrain shadows, snow, and glaciers. At the local scale, an adaptive dynamic segmentation strategy is proposed by establishing an equal-area buffer for each individual lake, where the temporal occurrence frequency of MNDWI is computed to build a stable water probability composite, and the Otsu algorithm is applied to independently derive lake-specific optimal thresholds. Using Landsat imagery and meteorological data from 1990 to 2025, we quantified the spatiotemporal dynamics of typical glacial lakes in the central Himalayas, and explored the driving mechanisms of climate factors on lake area changes. Over the past 35 years, the number and area of lakes have exhibited a pronounced expansion trend under a climatic regime characterized by rising temperatures, increasing precipitation, and decreasing relative humidity. During 1990–2020, lake area variations were primarily governed by strong interactions between temperature and wind speed. Summer variability exerted a more pronounced impact than winter variability. The proposed framework provides an effective approach for glacial lake extraction in the study area and may provide useful technical support for long-term monitoring of alpine lakes. Full article

This study presents an integrated, data-driven framework for satellite-derived bathymetry and morphodynamic assessment in large, regulated rivers, providing a spatial database to support reach-scale hydromorphological monitoring and river management. Satellite-derived bathymetry (SDB) was developed using 24,768 in situ depth measurements and Sentinel-2 multispectral data to train Random Forest (RF) and Artificial Neural Network (ANN) models. Under turbid water conditions, the Random Forest model outperformed the Artificial Neural Network model in simulating the non-linear relationship between the water spectrum and water depth; the RF model achieved an R² of 0.828 and an RMSE of 0.93 m, while the ANN model produced an R² of 0.608 and an RMSE of 1.40 m. Depth-dependent errors were smallest at intermediate depths and larger in shallow and deep water. Morphometric parameters, including the Sinuosity Index (SI) and Braiding Index (BI), were calculated for 2017, 2019, and 2021 using the NDWI-based water mask to define channel boundaries. The reach exhibited moderate sinuosity (SI ≈ 1.16), and an increase in braiding was observed (BI ranging from 1.33 to 1.36). From 2017 to 2019, erosion (3.51 km²) exceeded deposition (1.25 km²). In contrast, the 2019–2021 period showed approximately equal areas of erosion and deposition (1.63 km² each). The analysis is constrained by a single 2015 calibration survey, the optical penetration limit of Sentinel-2, and the reliance on three morphometric snapshots (2017, 2019, 2021), which may not capture short-term adjustments. The novelty of this study lies in integrating ML-based Sentinel-2 bathymetry with multi-temporal morphometric indicators to characterize the vertical and horizontal dynamics of regulated rivers jointly. Full article

The Qinghai Lake Basin (QLB) serves as a crucial ecological barrier on the Qinghai–Tibet Plateau, making high-precision mapping of land use/land cover (LULC) essential for eco-hydrological research within the basin. In this study, multitemporal Sentinel-1 radar and Sentinel-2 optical imagery from 2024, DEM-derived terrain information, and features derived from these sources were used to produce a 10-m resolution LULC map for the QLB using a support vector machine classifier. The Level-1 and Level-2 LULC datasets of QLB (QLBLC-10) achieved sample-based apparent overall accuracies (OAs) of 91.95% and 91.24%, respectively, and kappa coefficients of 0.90 for both. In contrast, the area-weighted apparent overall accuracy (OA_w) decreased to 81.50 ± 2.09% (95% confidence interval), indicating that class-area imbalance and small-area classes affect map-level performance. The ablation study confirms the contribution of multisource temporal information and terrain constraints to alpine LULC classification. The OA increased from 77.07% with single-temporal Sentinel-2 to 91.24% when multitemporal Sentinel-1/2 data and DEM-derived features were added, while the kappa coefficient increased from 0.75 to 0.90. The comparison with existing products shows that QLBLC-10 outperforms existing global and regional LULC datasets in representing alpine land cover patterns in the QLB. The LULC system proposed in this study is tailored to the QLB, and the presented LULC classification strategy enhances discrimination among major alpine vegetation types, including temperate and alpine steppes, alpine meadows, and alpine shrublands. It provides an up-to-date (2024) LULC dataset for ecosystem monitoring and land management across the QLB. Full article

Mediterranean and semi-arid mountain forests are increasingly affected by recurrent drought, wildfire, overgrazing, and anthropogenic pressure, with direct implications for forest sustainability. This study assesses the spatio-temporal dynamics of vegetation cover in the Ouled Yagoub Forest, Khenchela Province, northeastern Algeria, from 1994 to 2025, using GIS and remote sensing. Multi-temporal satellite images, including Landsat data for historical periods and Sentinel-2 data for recent years, were processed to calculate NDVI, classify NDVI-derived vegetation-cover classes, and detect vegetation changes before and after the 2021 wildfire. Vegetation-cover classes were quantified in hectares and percentages, and NDVI change maps were produced for the periods 1994–2000, 2000–2010, 2010–2020, 2020–2021, 2021–2022, 2021–2025, and 1994–2025. Results showed that dense vegetation increased from 14.15% in 1994 to 20.71% in 2020, indicating improved pre-fire vegetation conditions. After the 2021 wildfire, dense vegetation decreased to 17.44% in 2021 and 13.44% in 2022, while very low vegetation increased sharply to 29.79% in 2022. The 2021–2022 period showed the strongest negative vegetation response, with 32.65% of the mapped area classified as vegetation decrease. By 2025, partial recovery was observed, with vegetation increase covering 20.14% of the mapped area between 2021 and 2025. However, low vegetation remained dominant, indicating incomplete and spatially heterogeneous recovery. These findings highlight the usefulness of NDVI-based multi-temporal analysis for monitoring forest degradation, post-fire recovery, and priority areas for restoration planning in semi-arid Mediterranean mountain forests, while also supporting sustainability-oriented forest management in other fire-prone regions with comparable ecological constraints. Full article

Soil salinization is a major constraint on sustainable agricultural development in arid regions, yet soil salinity dynamics are commonly assessed using pixel-based remote sensing products that are difficult to relate to agricultural management units. To solve this problem, we developed an agricultural parcel-scale framework for soil salinity monitoring and mitigation assessment in Delingha City, Qinghai Province, China. Cropland parcels were extracted using a Recurrent Residual U-Net (R2U-Net) model, and soil salinity inversion for April during 2021–2025 was conducted by integrating Sentinel-1/2 imagery with a stacking ensemble learning model. The model incorporated Random Forest Regression (RFR), Gradient Boosting Regression (GBR), Multi-Layer Perceptron (MLP), and Support Vector Regression (SVR) to improve prediction accuracy and robustness. The selected features included vegetation indices, salinity indices, and SAR backscatter parameters. Among them, the Soil Adjusted Vegetation Index (SAVI) showed the strongest correlation with soil salinity, while Salinity Index 2 (SI2) exhibited the highest contribution to model performance. The R2U-Net achieved an F1-score of 0.8574 for parcel extraction. The ensemble model produced the best inversion results with an R² of 0.52 and reduced prediction errors compared with individual models. Results indicated an overall decline in soil salinity from 2021 to 2025, suggesting an improvement in soil salinity conditions during the study period. Parcel-scale aggregation reduced spatial noise; improved temporal stability; and revealed heterogeneous field responses, including salinity-declining, fluctuating, and increasing trends. The proposed framework enhances the interpretability and management relevance of soil salinity monitoring and provides practical support for precision agricultural management in arid regions. Full article

Mining-induced land subsidence poses significant geohazard risks to critical on-site mining operational support infrastructure, such as tailings storage facilities (TSFs). This study investigates the Doornpoort TSF subsidence at the South Deep gold mine in South Africa, using multi-temporal Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) and Non-negative Matrix Factorisation (NMF) algorithm approach to split the superimposed subsidence contributing drivers, alongside the incorporation of Global Navigation Satellite System (GNSS) data and underground mining layout plans. 78 Sentinel-1A Satellite Aperture Radar (SAR) ascending acquisitions between May 2022 and December 2024 were obtained and processed to determine the average annual deformation rates and cumulative time-series displacement for the study area. The InSAR-derived subsidence rates at the designated three benchmarks on the embankments of the Doornpoort TSF and TSF 1&2 are −26.09 mm/year, −13.40 mm/year and −16.25 mm/year, while the maximum cumulative subsidence was −57.45 mm, −42.76 mm and −36.44 mm. A comparison of the InSAR results with the GNSS-derived subsidence results showed correlation standard deviations of 1.87 mm, 0.93 mm, and 1.05 mm, respectively. The InSAR results revealed spatially coherent subsidence patterns and a good correlation between deformation boundaries and underground mining layouts, suggesting that mining-induced stress redistribution is the primary driver of regional surface subsidence. The NMF decomposition of the InSAR-derived deformation result at a selected benchmark on the Doornpoort TSF embankment, whose average annual deformation with a cumulative time series deformation of −26.09 mm/year and −57.45 mm, respectively, revealed that 92% of the observed cumulative deformation is associated directly with the underground mining, whilst the remaining 8% is associated with TSF embankment consolidation. Furthermore, the selected decomposition benchmark within the TSF basin showed that underground mining alone accounted for 100% of the observed subsidence there. These findings support a coupled deformation framework in which deep mining activities influence regional subsidence, while localised geological conditions modulate its surface manifestation. Full article

Facade thermal defect diagnosis is a critical prerequisite for energy-efficiency retrofitting of old residential buildings. However, conventional infrared thermography is easily affected by environmental conditions and occupant behavior, making it difficult to distinguish persistent thermal defects from transient anomalies. To address this challenge, this study proposes an integrated diagnostic framework for old residential buildings in Wuhan, China, combining unmanned aerial vehicle (UAV) infrared thermography, multi-temporal data acquisition, 3D flight-path planning, thermal anomaly recognition, facade spatial mapping, and temporal screening. Field experiments were conducted to determine key acquisition parameters, including sensor preheating time, imaging distance, and acquisition timing. Thermal anomalies were identified through image-processing techniques and mapped onto facade representations derived from 3D models. Repeated observations across different times and days were then used to evaluate anomaly recurrence and spatial stability. The results show that preheating the sensor for at least 10 min, maintaining a UAV-to-facade distance of 8–10 m, and acquiring data around 17:00 provide more reliable thermal images. Multi-temporal screening effectively reduces false positives caused by temporary disturbances, while persistent anomalies associated with window–wall joints, floor slabs, wall surfaces, and moisture-related areas can be identified more robustly. The proposed framework provides a practical workflow for facade thermal defect diagnosis and retrofit-oriented decision support. Full article

Orthophoto change detection is used to find real land cover changes in urban monitoring, disaster assessment, and environmental management. In practice, however, multi-temporal orthophotos are rarely identical in geometry and radiometry even after standard preprocessing. Small residual misregistration, local building displacement, shadow movement, and illumination differences can produce edge-like responses that look like change but do not correspond to any land cover transition. These false alarms increase manual checking costs and reduce the reliability of change maps. This study addresses that practical problem by proposing an attention-guided conditional adversarial framework, named Attention-GAN, for false alarm-resistant orthophoto change detection. The aim is not to detect small perturbations as changes but to detect real land cover changes while suppressing responses to nuisance variations that should be treated as unchanged. The framework integrates a multi-scale spatial attention module, a channel attention module, and a PatchGAN discriminator. It also introduces perturbation-negative training pairs, where controlled geometric and radiometric perturbations are applied to unchanged image pairs and assigned all-zero change masks. Experiments on LEVIR-CD, WHU-CD, and DSIFN-CD show competitive or moderately higher accuracy than the selected representative baselines, with F1 scores of 91.2%, 92.45%, and 93.18%, respectively. In the ablation experiment, the false change rate on perturbation-negative validation pairs is reduced to 4.9%. Repeated-run statistics and ablation results indicate that the proposed training strategy mainly improves robustness by reducing false alarms under the evaluated perturbation range. The results support the use of controlled nuisance perturbations as a reproducible way to train and evaluate false alarm resistance, while broader validation under real multi-view, seasonal, and cross-sensor distortions remains necessary. Full article

The Sumapaz páramo, the most extensive continuous páramo complex on a global scale and a strategic component in the hydrological regulation of central Colombia, is undergoing a progressive ecohydrological degradation whose integrated characterization through multitemporal biophysical indicators remains limited. To address this gap, the present study examines the transformation dynamics of the system by articulating four analytical components: precipitation modeling based on IDEAM stations (1995–2025), thermal trend analysis from WorldClim grids (2000–2024), multitemporal spectral analysis of four normalized difference indices (NDVI, NDWI, NDSI, NBR) derived from Landsat imagery (2000–2025), and Corine Land Cover cartography (2000–2018). The findings reveal a spatial decoupling between the precipitation distribution, which tends to shift toward lower altitudinal belts, and the storage areas in peat and Andosols of the páramo core, with a consequent reduction in effective recharge regardless of the total precipitated volume. Paradoxically, an almost complete contraction of surfaces with a positive water signal coexists with the expansion of photosynthetic activity, a phenomenon attributable to processes of shrub encroachment, thermophilization, and nutrient enrichment rather than to a functional recovery of the ecosystem. The cartographic analysis, in turn, confirms the advance of agricultural and livestock uses over native regulating covers. The convergence of these vectors configures a multivectorial degradation scenario that escapes monitoring based on a single index and that demands management strategies oriented simultaneously toward anthropic pressure, the spatial redistribution of precipitation, and the implementation of integrated ecohydrological surveillance systems. Full article

Accurate characterization of flood dynamics in large river–lake systems remains challenging due to the difficulty of simultaneously capturing inundation extent and water surface elevation (WSE) variations under rapidly changing hydrological conditions. This study develops an integrated Synthetic Aperture Radar (SAR) and wide-swath interferometric altimetry framework to reconstruct the spatiotemporal evolution and storage dynamics of the 2024 flood event in the East Dongting Lake system, China. Sentinel-1 SAR imagery is utilized to derive high-resolution inundation extent, while the Surface Water and Ocean Topography (SWOT) mission, equipped with the Ka-band Radar Interferometer (KaRIn), provides two-dimensional WSE observations. To improve SAR-based flood extraction in heterogeneous floodplain environments, an Adaptive Spatially-Constrained Fuzzy C-Means (AS-FCM) algorithm is proposed by incorporating adaptive spatial regularization and structure-aware neighborhood weighting. Quantitative evaluation demonstrates that the proposed method achieves the highest performance among the evaluated conventional approaches, with an Overall Accuracy of 93.6%, an Intersection over Union of 0.89, and a Kappa coefficient of 0.87. The multi-temporal inundation sequence reveals a distinct flood evolution pattern characterized by rapid expansion during the rising stage and gradual recession during the post-peak period. SWOT-derived WSE observations exhibit strong agreement with synchronous in situ measurements after bias adjustment, with a correlation coefficient of 0.988. By integrating SAR-derived inundation extent with temporally matched water-level observations constrained by bias-adjusted SWOT and in situ gauge data, an empirical WSE–area relationship ($R^2=0.937$) is established to reconstruct daily flood dynamics and estimate cumulative water storage variation. The results indicate that the East Dongting Lake floodplain played an important buffering role during the 2024 flood event, with cumulative storage variation reaching approximately $10.7{\mathrm{km}}^3$ during the peak stage. Overall, the proposed framework demonstrates strong potential for flood monitoring and hydrological storage assessment in complex river–lake systems. Full article

Monitoring the vertical progress of reinforced-concrete buildings supports construction management, urban analytics, and seismic exposure classification, yet camera-based floor counting faces two obstacles: public datasets depict almost exclusively completed structures, and the number of structurally finished floors is visually ambiguous while a building is still being erected. We reformulate building-height estimation as discrete floor-count classification from a single street-level facade image and assemble a 29,049-image multi-source corpus centered on the reinforced-concrete urban stock of Kazakhstan, including a 12-month, fixed-viewpoint sequence of 2255 frames that isolates invariance to construction stage, illumination, weather, and season. We formalize a reproducible annotation protocol for three recurring structural ambiguities—incomplete upper floors, rooftop superstructures, and open ground-level pilotis—and propose DINOv2-MSTS, a dual-branch architecture that aggregates multi-scale patch-token statistics from a frozen self-supervised backbone, trained with an Ordinal-Aware Annotation-Uncertainty (OAU) loss for which its Gaussian spread is learned rather than fixed. On the 5359-image Korter + Mendeley 21-category benchmark, the model attains 80% top-1 accuracy, 94% within $\pm 1$ floor accuracy, and 0.28-floor mean absolute error on this saturated 21-category task (a lower bound for buildings of 21 or more floors) using only 1.84 M trainable parameters, 165× fewer than a fully fine-tuned Vision Transformer, which it outperforms by eight accuracy points. On the separate 2255-frame IITU fixed-label robustness probe, it preserves the correct six-floor prediction in 91% of frames (0.09-floor MAE). The corpus, protocol, architecture, and loss together provide a reproducible benchmark for construction-stage building monitoring. Full article

To advance crop type mapping in support of global food and water security, this study compared three spectral configurations: (A) the full 60-band DLR Earth Sensing Imaging Spectrometer (DESIS) hyperspectral narrowband (HNB) dataset, (B) a 14-band subset of DESIS-derived HNBs aligned with the planned Landsat 10 (formerly Landsat Next) spectral configuration (400–1000 nm), and (C) DESIS-based simulations of Landsat 10 superspectral broadbands. The analysis was conducted in California’s Central Valley, hereafter referred to as “the Central Valley”, during the peak growing month of August. DESIS imagery from August 2021, 2022, and 2023 was used sequentially for model development, testing, and independent validation. Over these three years, DESIS provided extensive hyperspectral coverage of much of the 4 million hectares in the Central Valley’s. Analyses were performed on Google Earth Engine using two pixel-based supervised classifiers, Random Forest (RF) and Support Vector Machine (SVM), to differentiate three major crop classes: row crops, grapes and tree crops, and winter wheat/fallow/other. The highest overall accuracy (86%) was achieved using SVM in combination with either the full DESIS hyperspectral dataset or the 14 DESIS narrowbands corresponding to Landsat 10. This finding aligns with earlier studies showing a small number of strategically positioned narrowbands can be optimal for crop type classification. Use of the narrowband datasets resulted in substantially higher accuracy (overall accuracy of 86%) compared to the simulated Landsat 10 broadbands (overall accuracy of 75%), supporting previous studies highlighting the utility of narrowbands. Despite the high accuracy using August imagery, the study indicates more granular crop type classification will require multi-temporal observations spanning the full phenological cycle (June–October), especially for a large number of crop classes. Acquiring task-based hyperspectral imagery over such large areas throughout the growing season remains operationally challenging. In contrast, Landsat 10 superspectral imagery could provide routine coverage across seasons and years that is practical and scalable for future large area crop type mapping and agricultural monitoring. Full article

Conceptual Site Models (CSMs) are essential tools for characterizing contaminated sites, integrating hydrobiogeochemical information to support remediation planning. Historical datasets are often underutilized, while additional investigations can be costly, limiting our understanding of contaminant dynamics. This study aims to develop a sustainable and cost-effective framework for constructing an enhanced CSM of the Mantua Lakes through the integration of historical (2008) and recent (2024–2025) sediment and water quality datasets, resulting in more than 2000 data points. Objectives included the reconstruction of a 3D geological model (55 boreholes), the estimation of contaminant masses in sediments, and the evaluation of temporal trends in contaminant distribution and natural attenuation. Sediment cores (collected at 25 cm intervals) and surface water samples were analyzed for arsenic, cadmium, chromium, mercury, and heavy petroleum hydrocarbons. A harmonized set of 39 georeferenced points enabled a multi-temporal comparison. Voronoi polygons and volumetric calculations were used to estimate contaminant mass within sediment layers. Bathymetric and stratigraphic data, consisting of 458 depth points and 64 isobaths, were integrated into a 3D geodatabase and extended into a 4D framework to capture temporal evolution. Sediments exhibited overall reductions in contaminants, particularly cadmium and hydrocarbons, while arsenic and chromium showed localized variations. Water column concentrations mirrored sediment trends, indicating significant bioattenuation. Integrating historical and recent data strengthens CSMs, provides quantitative mass estimates, and offers a comprehensive framework for understanding contaminant dynamics, natural attenuation processes, and sustainable site management. Full article

To address the critical challenges of multi-scale temporal dynamics and sensor-intrusiveness in driver fatigue detection, this paper proposes the Multi-Temporal Fusion Attention Network (MTFA-Net). The framework integrates two core innovations: a Multi-scale Temporal Adaptive Fusion (MTAF) module that dynamically weights short-, mid-, and long-term behavioral features via a scene-aware modulator, and a Physiological–Behavioral Cross-modal Adversarial Alignment (PBCAA) network that implicitly infers latent physiological states (e.g., HRV) from facial videos using adversarial learning and mutual information maximization. Experimental results on RLDD and NTHU-DDD datasets demonstrate that MTFA-Net achieves state-of-the-art accuracy (92.8%) while maintaining high interpretability and real-time efficiency, providing a robust, non-intrusive solution for intelligent cockpit safety. Full article