Search Results (665)

Hybrid classification approaches, combining pixel-based and object-based classification models, are being increasingly adopted to overcome the inherent limitations of Very-High-Resolution (VHR) image analysis. This paper proposes a hybrid classification framework that integrates probabilistic pixel-based classification, object-based aggregation, and rule-based refinement to produce GIS-ready Land Use/Land Cover (LULC) maps specifically designed for urban and regional planning. WorldView-2 imagery is first processed using an AdaBoost classifier to derive pixel-level class memberships; these results are subsequently aggregated at the object level (OBIA classification), following segmentation. Beyond thematic labeling, a Stability Map is introduced to quantify intra-object classification reliability, enabling the spatial identification of unstable or heterogeneous objects. The novelty lies not only in the integration of pixel and object paradigms but also in the operational utility of the Stability Map. When combined with rule-based reasoning, it provides a decision-oriented GIS product. The results demonstrate superior classification accuracy and enhanced interpretability compared to standard pixel-based or object-based approaches, highlighting the framework’s relevance for geospatial data analysis and planning-oriented applications. Full article

Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes. Full article

Road extraction from high-resolution remote sensing imagery is fundamental to numerous practical applications, yet still faces notable challenges caused by label noise, particularly the underlabeling of rural roads within training datasets. End-to-end dense prediction networks deliver high efficiency and strong global context capture capability, yet they are highly vulnerable to such label noise. In contrast, patch-based methods achieve better robustness but sacrifice global reasoning ability and computational efficiency. This paper proposes a novel training strategy named Positive-guided Local Supervision (PLS), which integrates the strengths of the two aforementioned paradigms. PLS preserves the full end-to-end forward pass to leverage global context, while restricting loss computation to local patches centered on reliably annotated road pixels (positive samples) via a standard dense segmentation loss. By isolating the model from misleading gradients generated in underlabeled regions, PLS effectively mitigates the negative impact of underlabeling without compromising computational efficiency and prediction quality. We evaluate the proposed PLS on two datasets: the public DeepGlobe benchmark and a newly constructed challenging dataset, namely China Four Provinces (CH4P). CH4P includes 13,498 high-resolution images of rural China, which suffers from severe underlabeling inherited from public web maps. Extensive quantitative evaluations on DeepGlobe and the newly built CH4P dataset validate that our PLS strategy surpasses conventional end-to-end baselines and competitive state-of-the-art methods under both noisy original labels and manually refined annotations. On the refined DeepGlobe-mini-test and CH4P-mini-test subsets, PLS obtains prominent absolute IoU improvements of 0.127 and 0.104 over baseline models, respectively, showing distinct superiority in handling severe real-world underlabeling. Qualitative visualizations and cross-dataset generalization tests further demonstrate that PLS can effectively retrieve road segments omitted in raw annotations, delivers strong robustness against practical label noise, and introduces no extra computational burden in the inference stage. Full article

High-resolution satellite imagery is pivotal for accurate analysis in remote sensing applications, including land-use monitoring, urban planning, and environmental assessment. However, obtaining such data is often costly and limited. Consequently, super-resolution techniques, such as deep learning models and fine-tuning strategies like LoRA, offer a promising alternative to the critical research challenge, especially given the diversity and large scale of satellite datasets. While deep learning-based super-resolution models have been very promising recently, their effectiveness, efficiency, and scalability across heterogeneous satellite scenes are not well studied. This work studies the performance of representative deep learning Super-Resolution frameworks, including the Enhanced Super-Resolution Generative Adversarial Network. (ESRGAN), Swin Transformer for Image Restoration (SwinIR), and latent diffusion models (LDM), under unified experimental conditions using the WorldStrat dataset. The main goal is to establish whether adaptation strategies for parameter efficiency can boost reconstruction quality while reducing computational and training costs. Toward this goal, we investigate hybrid sequential pipelines, ensemble averaging, and Low-Rank Adaptation (LoRA)–based fine-tuning. The experiments indicate that these pipelines, which use multi-model methods, achieve only marginal performance gains while incurring substantial increases in computational complexity. LoRA-Based Fine-Tuning, by contrast, has demonstrated superiority in enhancing reconstruction accuracy and quality across all model families, despite using only a small percentage of trainable parameters. LoRA-based models demonstrate superiority over multi-model methods in both efficiency and performance. The presented results confirm that LoRA is an effective and accessible technique for high-fidelity satellite-based super-resolution image synthesis. The manuscript identifies LoRA as one of the enabling technologies advancing the state of the art in Deep Learning-based Super Resolution for large-scale satellite-based image synthesis. Full article

Coastal urbanization is increasingly constrained by legacy land-use patterns and escalating climate risks, yet long-term morphological trajectories remain poorly quantified due to the absence of multispectral data in pre-satellite archives. This study introduces a scalable deep learning pipeline that bridges a century-scale domain gap through an attention-enhanced Pix2Pix colorization stage and a few-shot U-Net++ segmentation stage, enabling automated reconstruction of urban expansion from panchromatic historical aerial imagery (1920–1971) and digital aerial photographs (1997) to contemporary very-high-resolution satellite data (2024) in Les Sables-d’Olonne, France. The novelty of the approach lies in coupling generative colorization with epoch-specific fine-tuning to overcome radiometric and annotation bottlenecks that have historically prevented quantitative urban reconstruction from pre-satellite archives. The colorization stage achieved high spectral fidelity (PSNR 35.21 dB, SSIM 0.9762), and segmentation performed strongly on modern imagery (mIoU 0.9789). While the segmentation model performed strongly on modern imagery, direct transfer to historical data exhibited substantial domain shift due to radiometric discrepancies. Few-shot adaptation on year-specific calibration sets recovered reliable building footprints (mIoU 0.53–0.65) across the full timeline. Multi-scalar analysis of the reconstructed footprints revealed constrained anisotropic expansion: early saturation of the coastal historic core, followed by rapid inland peri-urbanization post-1971 driven by geographic barriers. This spatiotemporal shift has entrenched spatial lock-in, placing recent development in retro-littoral zones that are vulnerable to submersion and characterized by severe vegetation loss. The framework unlocks previously inaccessible historical archives for quantitative urban monitoring, providing critical insights into legacy effects of unconstrained growth and informing resilient coastal planning under climate change. Full article

Glacial lake dynamics in high-mountain regions serve as a sensitive proxy for cryospheric responses to climate warming. This study utilizes multi-temporal Sentinel-2 imagery and digital elevation model (DEM) data to quantify glacial lake evolution in the Donglin Tsangpo Watershed, a strategically important section of the China–Nepal Economic Corridor, from 2016 to 2024. The results show a significant expansion in both the number (from 43 to 56) and total area (from 3.97 km² to 4.94 km², +24.43%) of glacial lakes, primarily driven by the rapid emergence of very small lakes (0.02–0.05 km²) and a clear upward shift in elevation distribution, with new lakes forming above 5300 m and extending to elevations exceeding 5500 m. Analysis of Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST) reveals that this expansion coincided with pronounced positive thermal anomalies, particularly the 2020 extreme warm event (daytime +3.88 °C, nighttime +1.61 °C). Mechanistic analysis using the ERA5-Land reanalysis dataset further demonstrates that persistent positive downward longwave radiation (LW) anomalies (peaking at +10.71 W/m² in 2021) effectively compensated for reduced shortwave input, inhibiting nocturnal refreezing and extending the effective ablation period. Furthermore, a rising liquid-to-solid precipitation ratio and extreme melt-day anomalies (up to +39.36 days) provided intensified hydrothermal inputs, driving the pronounced expansion of glacier-contact lakes despite non-linear interannual responses. This study also estimates individual lake volumes, identifying a transition toward rapid lake development that elevates potential downstream hazard exposure. These findings provide a high-resolution dataset and a robust physical framework for transboundary environmental monitoring and risk assessment in this climate-sensitive region. Full article

With the rapid and ongoing expansion of urban areas, the need for accurate, reliable, and regularly updated topographic maps has become increasingly critical for planning and sustainable development. While traditional aerial photogrammetry—whether analog or digital—has long been the standard for such tasks, it remains costly, time-consuming, and logistically demanding, particularly when large or inaccessible regions are involved. This study proposes an alternative approach based on very-high-resolution satellite imagery, focusing specifically on data acquired from Morocco’s Mohammed VI A and B satellites. The research evaluates the capacity of this satellite imagery to support large-scale topographic mapping, both in terms of geometric accuracy and the ability to identify essential urban features. To validate the results, we conducted a comparative analysis of satellite data with conventional photogrammetric imagery from analog cameras (RMK TOP) and digital sensors (ADS, DMC), using ground control points (GCPs) and differential GPS (DGPS) measurements for calibration and accuracy assessment. The outcomes demonstrate that planimetric accuracy from satellite imagery meets the required standards for mapping at 1:10,000 and 1:5000 scales. However, altimetric accuracy is closer to the upper permissible limits, especially in applications requiring finer detail. While major urban elements such as roads, buildings, and vegetation are well identified, smaller infrastructure components, such as power lines, remain challenging to detect. Despite these limitations, the study highlights the growing potential of satellite imagery as a cost-effective and operationally efficient alternative to traditional methods, particularly in rapidly evolving urban environments where frequent map updates are essential. Integration with GeoAI workflows is identified as a key direction for future research and is not part of the current methodology. Full article

Remote sensing is widely used in archaeological prospection to detect surface anomalies (crop marks) indicating buried remains, typically through recognition of visual patterns in high- or very high-resolution imagery acquired by means of satellite, airborne, or drone sensors. In contrast, spectroscopic approaches focusing on variations in spectral signatures still remain rarely applied in archaeological research. This study proposes a technological barrier-free method addressed to archaeologists which is based on pixel-level analysis of the Reflectance Values (RV) and spectral shape variations in the visible, near-infrared and short-wave infrared (VIS-NIR-SWIR) range derived from Sentinel-2 imagery. Spectral signatures are extracted through sampling polygons designed to account for the spatial resolution of the different Sentinel-2 bands and their spatial relationship with the location and size of the archaeological features. The RV method is tested on two Roman archaeological contexts: the ancient city of Telesia Vetere (San Salvatore Telesino, Benevento) and a Roman villa at Podere Colle Agnano (Labro, Rieti) using the full Sentinel-2 archive since 2017. While Telesia has previously been investigated through aerial photo interpretation and archaeological fieldwork, the Roman villa at Labro is documented here for the first time. Results show consistent seasonal repeated spectral separability between areas corresponding to known buried archaeological features and surrounding areas. Similar anomalies were also detected in areas without previously documented remains, thus suggesting the possible presence of buried structures and highlighting the predictive potential of the RV method. Owing to its easiness to use beyond image processing specialism and reliance on open-access data, the method can support archaeological decision-making and guide further investigation with higher-resolution remote sensing data or targeted field surveys, particularly in the framework of preventive archaeology. Full article

Forest fires pose a considerable threat to the security of ecosystems and human society, rendering accurate assessments of fire severity critical for ecological recovery and effective fire management. The differenced Normalized Burn Ratio (dNBR) has been employed to evaluate forest fire severity; however, it presents notable uncertainties owing to variations in data sources, temporal phases, and environmental factors. To address these challenges, this study analyzed 10 forest fires occurring between 2006 and 2023 in central Yunnan Province, China. First, a rapid sampling method utilizing very high-resolution imagery was developed to assess the performance of dNBR classification under varying conditions. Second, the study identified the optimal post-fire observation window and compared classification thresholds and accuracy between Landsat and Sentinel-2 imagery in assessing fire severity. Finally, the research explored the impacts of topographic correction and pre-fire vegetation differences on classification outcomes. The findings revealed the following: (1) Imagery captured in the spring of the fire year, characterized by minimal vegetation interference, demonstrated the highest classification stability and superior capability for identifying high-severity burns. (2) Landsat outperformed Sentinel-2 in regional accuracy (0.92 vs. 0.87), and direct threshold transfer between sensors resulted in a 39% underestimation of high-severity areas, underscoring the necessity for sensor-specific calibration. (3) Topographic correction provided limited practical benefits, merely yielding a marginal improvement in accuracy (+1.44%) with the SCS+C model in steep terrain, and was generally unnecessary. (4) The influence of pre-fire vegetation was discovered to be threshold-dependent: dNBR performed reliably in forests with pre-fire NDVI > 0.5, while adjusted approaches were solely recommended for sparse or heterogeneous vegetation. Overall, this study establishes a systematic framework for optimizing dNBR-based severity assessment, enhancing its accuracy and operational utility in forest fire management. Full article

Historical images as the dominant method for documenting the world and its inhabitants can help us to better understand the real history. Due to the limited camera technology, historical images captured in the early to mid-20th century tend to be very blurry, unclear, noisy, and obscure. The goal of this paper is to super-resolve images for historical image restoration. Compared to the degradations in modern digital imagery, those in historical images have unique features that are typically much more complex and less well understood. The discrepancy between historical images and modern high-definition digital images leads to a significant performance drop for existing super-resolution (SR) models trained on modern digital imagery. To tackle this problem, we propose a new method, namely DA-CycleGAN. Specifically, the DA-CycleGAN is built on top of CycleGAN to achieve unsupervised learning. We introduce a degradation-adaptive (DA) module with strong, flexible adaptation to learn various unknown degradations from samples. Moreover, we collect a large dataset containing 10,000 low-resolution images from real historical films. The dataset features various natural degradations. Our experimental results demonstrate the superior performance of DA-CycleGAN and the effectiveness of our image dataset for achieving accurate super-resolution enhancement of historical images. Full article

This study presents the development of a Python-based flood-susceptibility risk-mapping tool, implemented in Jupyter Notebook, applied to Rwanda. A Flood Susceptibility Index (FSI) was developed by integrating 20 causal factors associated with flood occurrences, including topographic, hydrological, geological, and anthropogenic variables. Logistic regression, and Variance Inflation Factor were implemented in Python using libraries such as Numpy, Arcpy, traceback, scipy, Pandas, Seaborn, and statsmodel to assign weights to each factor, and to address multicollinearity. The model was validated against flood extent data derived from Sentinel-1 satellite imagery for the major historical flood event that occurred from 2014 to 2024, ensuring spatial consistency and predictive reliability. To project future flood susceptibility for 2030, precipitation data from the Institut Pierre Simon Laplace Coupled Model, version 5A, Medium Resolution (IPSL-CM5A-MR) climate model under the Representative Concentration Pathway 8.5 (RCP 8.5) scenario were utilized. The resulting FSI was classified into five susceptibility levels, from very low to very high, and visualized using Python’s geospatial and plotting tools within Jupyter Notebook in ArcGIS Pro 3.5. It indicates that areas with high amounts of rainfall, and proximity to wetlands and rivers reveal the highest flood risk. The automated and reproducible approach offered by Python enhances transparency and scalability, providing a decision-support tool for disaster risk reduction and climate adaptation planning in Rwanda. Full article

Oil spills are severe environmental disasters that cause long-lasting damage to marine ecosystems and impose significant economic costs, underscoring the urgent need for efficient detection and monitoring technologies. Conventional field-based observation methods, while valuable, are constrained by limited spatial coverage, high costs, and labor-intensive processes, making them impractical for large-scale or rapid-response applications. To overcome these challenges, satellite remote sensing has been used as an effective alternative for oil spill monitoring. In particular, the advent of Google Earth Engine (GEE), a cloud-based geospatial platform, has transformed oil spill research by enabling scalable management and analysis of large satellite remote sensing datasets. This review synthesizes studies employing GEE for oil spill detection, across marine environments and interconnected aquatic systems, focusing on methodologies based on optical imagery and synthetic aperture radar data and approaches that integrate machine learning techniques. The analysis underscores that GEE enhances oil spill monitoring by facilitating rapid data processing, supporting reproducible workflows, and expanding access to multi-source satellite data. Furthermore, this review highlights the necessity of incorporating very-high-resolution satellite data and achieving tighter integration of external deep learning framework within GEE to improve detection accuracy and the operational applicability in complex marine and coastal contexts. Full article

Very-high-resolution (VHR) land cover mapping in highly heterogeneous regions faces critical challenges including strong annotation dependence, significant image heterogeneity, and insufficient spectral information. To address these challenges, this study proposes a novel framework integrating remote sensing foundation models with multi-source data Bayesian fusion for VHR land cover mapping in the Pearl River Delta (PRD), which is one of the most complex and heterogeneous landscapes in China. To implement this framework, we first construct three datasets including PRD262K containing 262,436 unlabeled VHR images for pretraining, PRDLC-PRO with 33,342 annotated samples for semantic segmentation, and a 15,000-point sample set for medium-resolution (MR) classification. A Segmentation-Driven Masked AutoEncoder (SDMAE) is developed to learn robust feature representations from large-scale unlabeled VHR imagery, which is subsequently integrated with a Scene-Based Feature Network (SBFNet) to capture multi-scale semantic features for accurate land cover segmentation. Finally, a decision-level Bayesian fusion method is proposed to effectively integrate the fine spatial details of VHR imagery with the spectral stability of MR data. Experiments demonstrate that the proposed framework outperforms existing methods across multiple datasets, achieving an overall accuracy of 87.98% and mIoU of 66.61% on PRDLC-PRO. The subsequent decision-level Bayesian fusion further enhances spatial consistency and robustness, providing an effective solution for large-scale VHR land cover mapping in highly heterogeneous regions with limited annotations. Full article

Precise estimation of evapotranspiration (ET) is essential for sustainable water management in arid agroecosystems, particularly for high-water-demand crops such as rice. This study integrated very-high-resolution UAV thermal–multispectral imagery with a Two-Source Energy Balance model (UAV–TSEB) and a field-calibrated AquaCrop model to quantify daily ET and its components under continuous flooding on the arid Peruvian coast during the 2024–2025 season. A network of 24 drainage lysimeters provided an independent observational benchmark (ET_lys); to represent the treatment-level response, lysimeter observations were aggregated as the mean across the 24 units for each UAV campaign. Thirteen UAV surveys supplied radiometric surface temperature and biophysical inputs (e.g., NDVI and fractional cover) to derive spatially explicit ET, while AquaCrop provided continuous daily simulations between flight dates. Direct lysimeter-based validation indicated high agreement for AquaCrop (R² = 0.85; RMSE = 0.26 mm d⁻¹; MBE = 0.01 mm d⁻¹) and moderate agreement for UAV–TSEB (R² = 0.66; RMSE = 0.81 mm d⁻¹; MBE = 1.01 mm d⁻¹). Model intercomparison further showed consistent temporal dynamics of ET (R² = 0.70; RMSE = 1.35 mm d⁻¹) and robust partitioning of crop transpiration (R² = 0.79; RMSE = 0.99 mm d⁻¹) and soil evaporation (R² = 0.76; RMSE = 1.03 mm d⁻¹) while revealing a systematic divergence under near-complete canopy cover: AquaCrop tended to suppress evaporation, whereas UAV–TSEB detected residual evaporation from the flooded surface. Overall, the results highlight the complementarity of both approaches—UAV–TSEB as a spatial diagnostic tool and AquaCrop as a temporally continuous simulator—providing a robust framework for ET monitoring, flux partitioning, and water-use-efficiency assessment in water-scarce rice systems. Full article

The accurate estimation of tree canopy volume is fundamental in precision agriculture for quantifying vegetation structure, biomass, and productivity in perennial cropping systems. This study investigates a shadow geometry approach for estimating olive tree canopy volumes from a single, very high-resolution WorldView-3 multispectral image. The method integrates multispectral classification for canopy and shadow delineation with a geometric model that infers canopy height from shadow measurements, accounting for solar position and terrain morphology. Two classification strategies were evaluated: object-based image analysis (OBIA) and pixel-based (PB) classification, each applied to the original eight-band multispectral image and to a derived dataset enriched with vegetation indices (NDVI—Normalized Difference Vegetation Index; NDRE—Normalized Difference Red Edge Index) and principal component analysis (PCA) components. The canopy volume was estimated by integrating classified canopy and shadow areas with shadow-derived canopy height. The methodology was tested in a Mediterranean olive orchard and validated against UAV-derived point clouds for approximately 700 trees. The results indicate that the approach captures spatial variability in canopy structure. The Object-Based Image Analysis (OBIA) applied to filtered PCA-enhanced imagery achieved the highest accuracy in canopy volume estimation (RMSE = 2.04 m³; R² = 0.56), outperforming the alternative pixel-based (PB) classification applied to the original multispectral data. Overall, the study demonstrates the potential of single-image WorldView-3 data for rapid and scalable three-dimensional canopy characterization in precision agriculture. Full article