Search Results (7,403)

Levees are critical for flood defence, but their integrity is threatened by hazards such as piping and seepage, especially during high-water-level periods. Traditional manual inspections for these hazards and associated emergency response elements, such as personnel and assets, are inefficient and often impractical. While UAV-based remote sensing offers a promising alternative, the effective fusion of multi-modal data and the scarcity of labelled data for supervised model training remain significant challenges. To overcome these limitations, this paper reframes levee monitoring as an unsupervised anomaly detection task. We propose a novel, fully automated framework that unifies geophysical hazards and emergency response elements into a single analytical category of “abnormal targets” for comprehensive situational awareness. The framework consists of three key modules: (1) a state-of-the-art registration algorithm to precisely align infrared and visible images; (2) a generative adversarial network to fuse the thermal information from IR images with the textural details from visible images; and (3) an adaptive, unsupervised segmentation module where a mean-shift clustering algorithm, with its hyperparameters automatically tuned by Bayesian optimization, delineates the targets. We validated our framework on a real-world dataset collected from a levee on the Pajiang River, China. The proposed method demonstrates superior performance over all baselines, achieving an Intersection over Union of 0.348 and a macro F1-Score of 0.479. This work provides a practical, training-free solution for comprehensive levee monitoring and demonstrates the synergistic potential of multi-modal fusion and automated machine learning for disaster management. Full article

Multi-modal image segmentation is a key task in various fields such as urban planning, infrastructure monitoring, and environmental analysis. However, it remains challenging due to complex scenes, varying object scales, and the integration of heterogeneous data sources (such as RGB, depth maps, and infrared). To address these challenges, we proposed a novel multi-modal segmentation framework, DyFuseNet, which features dynamic adaptive windows and cross-scale feature fusion capabilities. This framework consists of three key components: (1) Dynamic Window Module (DWM), which uses dynamic partitioning and continuous position bias to adaptively adjust window sizes, thereby improving the representation of irregular and fine-grained objects; (2) Scale Context Attention (SCA), a hierarchical mechanism that associates local details with global semantics in a coarse-to-fine manner, enhancing segmentation accuracy in low-texture or occluded regions; and (3) Hierarchical Adaptive Fusion Architecture (HAFA), which aligns and fuses features from multiple modalities through shallow synchronization and deep channel attention, effectively balancing complementarity and redundancy. Evaluated on benchmark datasets (such as ISPRS Vaihingen and Potsdam), DyFuseNet achieved state-of-the-art performance, with mean Intersection over Union (mIoU) scores of 80.40% and 80.85%, surpassing MFTransNet by 1.91% and 1.77%, respectively. The model also demonstrated strong robustness in challenging scenes (such as building edges and shadowed objects), achieving an average F1 score of 85% while maintaining high efficiency (26.19 GFLOPs, 30.09 FPS), making it suitable for real-time deployment. This work presents a practical, versatile, and computationally efficient solution for multi-modal image analysis, with potential applications beyond remote sensing, including smart monitoring, industrial inspection, and multi-source data fusion tasks. Full article

Unmanned aerial vehicle (UAV) imagery provides an efficient approach for monitoring cotton defoliation and boll-opening rates. Deep learning, particularly convolutional neural networks (CNNs), has been widely applied in image processing and agricultural monitoring, achieving strong performance in tasks such as disease detection, weed recognition, and yield prediction. However, existing models often suffer from heavy computational costs and slow inference speed, limiting their real-time deployment in agricultural fields. To address this challenge, we propose a lightweight cotton maturity recognition model, RTCMNet (Real-time Cotton Monitoring Network). By incorporating a multi-scale convolutional attention (MSCA) module and an efficient feature fusion strategy, RTCMNet achieves high accuracy with substantially reduced computational complexity. A UAV dataset was constructed using images collected in Xinjiang, and the proposed model was benchmarked against several state-of-the-art networks. Experimental results demonstrate that RTCMNet achieves 0.96 and 0.92 accuracy on defoliation rate and boll-opening rate classification tasks, respectively. Meanwhile, it contains only 0.35 M parameters—94% fewer than DenseNet121—and only requires an inference time of 33 ms, representing a 97% reduction compared to DenseNet121. Field tests further confirm its real-time performance and robustness on UAV platforms. Overall, RTCMNet provides an efficient and low-cost solution for UAV-based cotton maturity monitoring, supporting the advancement of precision agriculture. Full article

Soil erosion is an increasingly severe problem and a global focus. As one of the countries facing relatively serious soil erosion, China encounters significant ecological challenges. This study focuses on the carbon sink benefits of comprehensive soil and water conservation management in the red soil erosion area of southern China, conducting an in-depth analysis using the Ziyang small watershed in Shangyou County, Jiangxi Province, as a typical case. Research methods involved constructing an integrated monitoring approach combining basic data, measured data, and remote sensing data. Changes in soil and vegetation carbon storage in the Ziyang small watershed across different years were determined by establishing a baseline scenario and applying inverse distance spatial interpolation, quadrat calculation, feature extraction, and screening. The results indicate that from 2002 to 2023, after 21 years of continuous implementation of various soil and water conservation measures under comprehensive watershed management, the carbon storage of the Ziyang small watershed increased significantly, yielding a net carbon sink of 54,537.28 tC. Tending and Management of Coniferous and Broad-leaved Mixed Forest, Low-efficiency Forest Improvement, and Thinning and Tending contributed substantially to the carbon sink, accounting for 72.72% collectively. Furthermore, the carbon sink capacity of the small watershed exhibited spatial variation influenced by management measures: areas with high carbon density were primarily concentrated within zones of Tending and Management of Coniferous and Broad-leaved Mixed Forest, while areas with low carbon density were mainly found within zones of Bamboo Forest Tending and Reclamation. The increase in watershed carbon storage was attributed to contributions from both vegetation and soil carbon pools. Comprehensive management of soil erosion demonstrates a significant carbon accumulation effect. The annual growth rate of vegetation carbon storage was higher than that of soil carbon storage, yet the proportion of soil carbon storage increased yearly. This study provides a theoretical basis and data foundation for the comprehensive management of soil and water conservation in small watersheds in the southern red soil erosion region of China and can offer technical and methodological support for other soil and water conservation carbon sink projects in this area. Full article

Climate change is intensifying fire regimes, thereby challenging forest ecosystems and making it more difficult to predict the fate of burned trees. The significant ecological impacts of latent tree mortality remain poorly understood. In this study, we reviewed the scientific literature on latent tree mortality in conifer forests following wildfires or prescribed fires. A total of 2294 papers published between 2000 and 2024 were identified from Scopus and Web of Science databases. Using the PICO selection method, we included 16 relevant studies in the final analysis. These studies are based on field assessment, excluding remote sensing and controlled laboratory conditions. Our research revealed that latent mortality results from multiple forms of damage and environmental stressors that disrupt hydraulic function and carbon allocation, increasing tree vulnerability to secondary biotic and abiotic stressors. The discussion is structured around four thematic areas: physiology, ecophysiology, dendrochronology, and silviculture. This approach contributes to a deeper, interdisciplinary understanding of latent tree mortality. However, predicting it remains difficult, reflecting persistent knowledge gaps. Despite the limited literature on this specific field, our review highlights the need for integrated physiological indicators, such as sap flow, transpiration, nonstructural carbohydrates and glucose concentration, as well as long-term monitoring along many growing seasons to better assess tree survival after fire. Full article

The responsibility for risk assessment and user safety in forested and recreational areas lies with the property owner. This study shows that unmanned aerial vehicles (UAVs), combined with remote sensing and GIS analysis, effectively support the identification of high-risk trees, particularly those with reduced structural stability. UAV-based surveys successfully detect 78% of dead or declining trees identified during ground inspections, while significantly reducing labor and enabling large-area assessments within a short timeframe. The study covered an area of 6.69 ha with 51 reference trees assessed on the ground. Although the multispectral camera also recorded the red-edge band, it was not included in the present analysis. Compared to traditional ground-based surveys, the UAV-based approach reduced fieldwork time by approx. 20–30% and labor costs by approx. 15–20%. Orthomosaics generated from images captured by commercial multispectral drones (e.g., DJI Mavic 3 Multispectral) provide essential information on tree condition, especially mortality indicators. UAV data collection is fast and relatively low-cost but requires equipment capable of capturing high-resolution imagery in specific spectral bands, particularly near-infrared (NIR). The findings suggest that UAV-based monitoring can enhance the efficiency of large-scale inspections. However, ground-based verification remains necessary in high-traffic areas where safety is critical. Integrating UAV technologies with GIS supports the development of risk management strategies aligned with the principles of precision forestry, enabling sustainable, more proactive and efficient monitoring of tree-related hazards. Full article

Recovery from disasters is the complex process requiring coordinated measures to restore infrastructure, services and quality of life. While remote sensing is a well-established means for damage assessment, so far very few studies have shown how satellite imagery can be used by technical officers of affected countries to provide crucial, up-to-date information to monitor the reconstruction progress and natural restoration. To address this gap, the present study proposes a multi-temporal observatory method relying on GIS, change detection techniques and open and free multi-sensor satellite imagery to generate thematic maps documenting, over time, the impact and recovery from hydrological disasters such as hurricanes, tropical storms and induced flooding. The demonstration is carried out with regard to Hurricane Matthew, which struck Haiti in October 2016 and triggered a humanitarian crisis in the Sud and Grand’Anse regions. Synthetic Aperture Radar (SAR) amplitude change detection techniques were applied to pre-, cross- and post-disaster Sentinel-1 image pairs from August 2016 to September 2020, while optical Sentinel-2 images were used for verification and land cover classification. With regard to inundated areas, the analysis allowed us to determine the needed time for water recession and rural plain areas to be reclaimed for agricultural exploitation. With regard to buildings, the cities of Jérémie and Les Cayes were not only the most impacted areas, but also were those where most reconstruction efforts were made. However, some instances of new settlements located in at-risk zones, and thus being susceptible to future hurricanes, were found. This result suggests that the thematic maps can support policy-makers and regulators in reducing risk and making the reconstruction more resilient. Finally, to evaluate the replicability of the proposed method, an example at a country-scale is discussed with regard to the June 2023 flooding event. Full article

The integration of unmanned aerial vehicles (UAVs) and deep learning (DL) has significantly advanced crop disease detection by enabling scalable, high-resolution, and near real-time monitoring within precision agriculture. This systematic review analyzes peer-reviewed literature indexed in the Web of Science Core Collection as articles or proceeding papers through 2024. The main selection criterion was combining “unmanned aerial vehicle*” OR “UAV” OR “drone” with “deep learning”, “agriculture” and “leaf disease” OR “crop disease”. Results show a marked surge in publications after 2019, with China, the United States, and India leading research contributions. Multirotor UAVs equipped with RGB sensors are predominantly used due to their affordability and spatial resolution, while hyperspectral imaging is gaining traction for its enhanced spectral diagnostic capability. Convolutional neural networks (CNNs), along with emerging transformer-based and hybrid models, demonstrate high detection performance, often achieving F1-scores above 95%. However, critical challenges persist, including limited annotated datasets for rare diseases, high computational costs of hyperspectral data processing, and the absence of standardized evaluation frameworks. Addressing these issues will require the development of lightweight DL architectures optimized for edge computing, improved multimodal data fusion techniques, and the creation of publicly available, annotated benchmark datasets. Advancements in these areas are vital for translating current research into practical, scalable solutions that support sustainable and data-driven agricultural practices worldwide. Full article

Real-time, accurate and detailed monitoring of urban green space is of great significance for constructing the urban ecological environment and maximizing ecological benefits. Although high-resolution remote sensing technology provides rich ground object information, it also makes the surface information of urban green spaces more complex. Existing classification methods often struggle to meet the requirements of classification accuracy and the automation demands of high-resolution images. This study utilized GF-7 remote sensing imagery to construct an urban green space classification method for Beijing. The study used the YOLO v8 model as the framework to conduct a fine classification of urban green spaces within the Fifth Ring Road of Beijing, distinguishing between evergreen trees, deciduous trees, shrubs and grasslands. The aims were to address the limitations of insufficient model fit and coarse-grained classifications in existing studies, and to improve vegetation extraction accuracy for green spaces in northern temperate cities (with Beijing as a typical example). The results show that the overall classification accuracy of the trained YOLO v8 model is 89.60%, which is 25.3% and 28.8% higher than that of traditional machine learning methods such as Maximum Likelihood and Support Vector Machine, respectively. The model achieved extraction accuracies of 92.92%, 93.40%, 87.67%, and 93.34% for evergreen trees, deciduous trees, shrubs, and grasslands, respectively. This result confirms that the combination of deep learning and high-resolution remote sensing images can effectively enhance the classification extraction of urban green space vegetation, providing technical support and data guarantees for the refined management of green spaces and “garden cities” in megacities such as Beijing. Full article

This study explores the potential of Digital Earth Africa (DE Africa) coastlines products for assessing the Coastal Vulnerability Index (CVI) along the Casablanca coastline, Morocco. The analysis integrates remotely sensed shoreline data with elevation, slope, and geomorphological information from ASTER GDEM and geological maps within a GIS environment. Shoreline change metrics, including Shoreline Change Envelope (SCE), Net Shoreline Movement (NSM), Linear Regression Rate (LRR), and End Point Rate (EPR), were used to evaluate erosion trends from 2000 to 2023. Results show that sandy beach areas, particularly those below 12 m elevation, are highly exposed to erosion (up to 1.5 m/yr) and vulnerable to coastal hazards. Approximately 44% and 23% of the study area were classified as having very high and high vulnerability, respectively. The results indicate that remotely sensed data and GIS techniques are valuable and cost-effective tools for multi-scale geo-hazard coastal assessment studies. The study demonstrates that DE Africa products, combined with local landscape data, provide a valuable tool for coastal vulnerability assessment and monitoring in Africa. Full article

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

Accurate assessment of a crop’s water requirement is essential for optimising irrigation scheduling and increasing the sustainability of water use. The crop coefficient (K_c) is a dimensionless factor that converts reference evapotranspiration (ET₀) into actual crop evapotranspiration (ET_c) and is widely used for irrigation scheduling. The K_c reflects canopy cover, phenology, and crop type/variety, but is difficult to measure directly in heterogeneous perennial systems, such as vineyards. Remote sensing (RS) products, especially open-source satellite imagery, offer a cost-effective solution at moderate spatial and temporal scales, although their application in vineyards has been relatively limited due to the large pixel size (~100 m²) relative to vine canopy size (~2 m²). This study aimed to improve grapevine K_c predictions using vegetation indices derived from harmonised Sentinel-2 imagery in combination with spectral unmixing, with ground data obtained from canopy light interception measurements in three winegrape cultivars (Shiraz, Cabernet Sauvignon, and Chardonnay) in the Barossa and Eden Valleys, South Australia. A linear spectral mixture analysis approach was taken, which required estimation of vine canopy cover through beta regression models to improve the accuracy of vegetation indices that were used to build the K_c prediction models. Unmixing improved the prediction of seasonal K_c values in Shiraz (R² of 0.625, RMSE = 0.078, MAE = 0.063), Cabernet Sauvignon (R² = 0.686, RMSE = 0.072, MAE = 0.055) and Chardonnay (R² = 0.814, RMSE = 0.075, MAE = 0.059) compared to unmixed pixels. Furthermore, unmixing improved predictions during the early and late canopy growth stages when pixel variability was greater. Our findings demonstrate that integrating open-source satellite data with machine learning models and spectral unmixing can accurately reproduce the temporal dynamics of K_c values in vineyards. This approach was also shown to be transferable across cultivars and regions, providing a practical tool for crop monitoring and irrigation management in support of sustainable viticulture. Full article

Land cover mapping is essential for territorial management due to its links with ecological, hydrological, climatic, and socioeconomic processes. Traditional methods use discrete classes per pixel, but this study proposes estimating cover fractions with Sentinel-2 imagery (20 m) and AI. We employed the French Land cover from Aerospace ImageRy (FLAIR) dataset (810 km² in France, 19 classes), with labels co-registered with Sentinel-2 to derive precise fractional proportions per pixel. From these references, we generated training sets combining spectral bands, derived indices, and auxiliary data (climatic and temporal variables). Various machine learning models—including XGBoost three deep neural network (DNN) architectures with different depths, and convolutional neural networks (CNNs)—were trained and evaluated to identify the optimal configuration for fractional cover estimation. Model validation on the test set employed RMSE, MAE, and R² metrics at both pixel level (20 m Sentinel-2) and scene level (100 m FLAIR). The training set integrating spectral bands, vegetation indices, and auxiliary variables yielded the best MAE and RMSE results. Among all models, DNN2 achieved the highest performance, with a pixel-level RMSE of 13.83 and MAE of 5.42, and a scene-level RMSE of 4.94 and MAE of 2.36. This fractional approach paves the way for advanced remote sensing applications, including continuous cover-change monitoring, carbon footprint estimation, and sustainability-oriented territorial planning. Full article

Coastal debris is a global environmental issue that requires systematic monitoring strategies based on reliable statistical data. Recent advances in remote sensing and deep learning-based object detection have enabled the development of efficient coastal debris monitoring systems. In this study, two state-of-the-art object detection models—RT-DETR and YOLOv10—were applied to UAV-acquired images for coastal debris detection. Their false positive characteristics were analyzed to provide guidance on model selection under different coastal environmental conditions. Quantitative evaluation using mean average precision (mAP@0.5) showed comparable performance between the two models (RT-DETR: 0.945, YOLOv10: 0.957). However, bounding box label accuracy revealed a significant gap, with RT-DETR achieving 80.18% and YOLOv10 only 53.74%. Class-specific analysis indicated that both models failed to detect Metal and Glass and showed low accuracy for fragmented debris, while buoy-type objects with high structural integrity (Styrofoam Buoy, Plastic Buoy) were consistently identified. Error analysis further revealed that RT-DETR tended to overgeneralize by misclassifying untrained objects as similar classes, whereas YOLOv10 exhibited pronounced intra-class confusion in fragment-type objects. These findings demonstrate that mAP alone is insufficient to evaluate model performance in real-world coastal monitoring. Instead, model assessment should account for training data balance, coastal environmental characteristics, and UAV imaging conditions. Future studies should incorporate diverse coastal environments and apply dataset augmentation to establish statistically robust and standardized monitoring protocols for coastal debris. Full article

Gully erosion, driven by the interplay of natural processes and human activities, results in severe soil degradation and landscape alteration, yet approaches for accurately quantifying erosion triggered by extreme precipitation using multi-source high-resolution remote sensing remain limited. This study first extracted digital surface models (DSM) for the years 2014 and 2024 using Ziyuan-3 and GaoFen-7 satellite stereo imagery, respectively. Subsequently, the DSM was calibrated using high-resolution unmanned aerial vehicle photogrammetry data to enhance elevation accuracy. Based on the corrected DSMs, gully erosion depths from 2014 to 2024 were quantified. Erosion patches were identified through a deep learning framework applied to GaoFen-1 and GaoFen-2 imagery. The analysis further explored the influences of natural processes and anthropogenic activities on elevation changes within the gully erosion watershed. Topographic monitoring in the Sandu River watershed revealed a net elevation loss of 2.6 m over 2014–2024, with erosion depths up to 8 m in some sub-watersheds. Elevation changes are primarily driven by extreme precipitation-induced erosion alongside human activities, resulting in substantial spatial variability in surface lowering across the watershed. This approach provides a refined assessment of the spatial and temporal evolution of gully erosion, offering valuable insights for soil conservation and sustainable land management strategies in the Loess Plateau region. Full article