Search Results (573)

The growing availability of spatial data from remote sensing, laser scanning (LiDAR), and photogrammetric techniques stimulates the dynamic development of methods for the automatic detection and classification of topographic objects. In recent years, both classical machine learning (ML) algorithms and deep learning (DL) methods have found wide application in the analysis of large and complex data sets. Despite significant achievements, literature on the subject remains scattered, and a comprehensive review that systematically compares algorithm classes with respect to data modality, performance, and application context is still needed. The aim of this article is to provide a critical analysis of the current state of research on the use of ML and DL algorithms in the detection and classification of topographic objects. The theoretical foundations of selected methods, their applications to various data sources, and the accuracy and computational requirements reported in the literature are presented. Attention is paid to comparing classical ML algorithms (including SVM, RF, KNN) with modern deep architectures (CNN, U-Net, ResNet), with respect to different data types such as satellite imagery, aerial orthophotos, and LiDAR point clouds, indicating their effectiveness in the context of cartographic and elevation data. The article also discusses the main challenges related to data availability, model interpretability, and computational costs, and points to promising directions for further research. The summary of the results shows that DL methods are frequently reported to achieve several to over ten percentage points higher segmentation and classification accuracy than classical ML approaches, depending on data type and object complexity, particularly in the analysis of raster data and LiDAR point clouds. The conclusions emphasize the practical significance of these methods for spatial planning, infrastructure monitoring, and environmental management, as well as their potential in the automation of topographic analysis. Full article

Water resource monitoring can provide beneficial information supporting water management; however, present operational systems are small and provide only a subset of the information needed. Primary advancements consist of the clear explanation of water redistribution and water use from groundwater and river schemes, achieving better spatial detail and increased precision as evaluated against hydrometric observation. In such cases, Earth Observation (EO) satellite systems are persistently creating extensive data, which is now essential for applications in different fields. With readily available open-source satellite imagery, aerial remote sensing is progressively becoming a quick and efficient tool for monitoring land and water resource development actions, demonstrating time and cost savings. At present, the deep learning (DL) model will be beneficial for monitoring water resources and EO utilizing remote sensing. In this paper, a Deep Neural Network-Based Object Detection for Water Resource Monitoring and Earth Observation (DNNOD-WRMEO) model is introduced. The main intention is to develop an effective monitoring and analysis framework for water resources and Earth surface observations using aerial remote sensing images. Initially, the Wiener filter (WF) model was used for image pre-processing. For object detection, the Yolov12 method was used for identifying, locating, and classifying objects within an image, followed by the DNNOD-WRMEO methodology, which implements the ResNet-CapsNet model for the backbone feature extraction method. Finally, the temporal convolutional network (TCN) model was implemented for the classification of water resources. The comparison analysis of the DNNOD-WRMEO methodology exhibited a superior accuracy value of 98.61% compared with existing models under the AIWR dataset. Full article

Remote sensing enables large-scale, image-based assessments of river dynamics, offering new opportunities for hydrological monitoring. We present a publicly available dataset consisting of 281,024 satellite and aerial images of U.S. rivers, constructed using an Application Programming Interface (API) and the U.S. Geological Survey’s National Hydrography Dataset. The dataset includes images, primary keys, and ancillary geospatial information. We use a manually labeled subset of the images to train models for detecting rapids, defined as areas where high velocity and turbulence lead to a wavy, rough, or even broken water surface visible in the imagery. To demonstrate the utility of this dataset, we develop an image segmentation model to identify rivers within images. This model achieved a mean test intersection-over-union ($IoU$) of 0.57, with performance rising to an actual $IoU$ of 0.89 on the subset of predictions with high confidence (predicted $IoU$ > 0.9). Following this initial segmentation of river channels within the images, we trained several convolutional neural network (CNN) architectures to classify the presence or absence of rapids. Our selected model reached an accuracy and F1 score of 0.93, indicating strong performance for the classification of rapids that could support consistent, efficient inventory and monitoring of rapids. These data provide new resources for recreation planning, habitat assessment, and discharge estimation. Overall, the dataset and tools offer a foundation for scalable, automated identification of geomorphic features to support riverine science and resource management. Full article

With rapid advancements in sub-meter satellite and aerial imaging technologies, high-resolution remote sensing imagery has become a pivotal source for geospatial information acquisition. However, current semantic segmentation models encounter two primary challenges: (1) the inherent trade-off between capturing long-range global context and preserving precise local structural details—where excessive reliance on downsampled deep semantics often results in blurred boundaries and the loss of small objects and (2) the difficulty in modeling complex scenes with extreme scale variations, where objects of the same category exhibit drastically different morphological features. To address these issues, this paper introduces MAFMamba, a multi-scale adaptive fusion visual Mamba network tailored for high-resolution remote sensing images. To mitigate scale variation, we design a lightweight hybrid encoder incorporating an Adaptive Multi-scale Mamba Block (AMMB) in each stage. Driven by a Multi-scale Adaptive Fusion (MSAF) mechanism, the AMMB dynamically generates pixel-level weights to recalibrate cross-level features, establishing a robust multi-scale representation. Simultaneously, to strictly balance local details and global semantics, we introduce a Global–Local Feature Enhancement Mamba (GLMamba) in the decoder. This module synergistically integrates local fine-grained features extracted by convolutions with global long-range dependencies modeled by the Visual State Space (VSS) layer. Furthermore, we propose a Multi-Scale Cross-Attention Fusion (MSCAF) module to bridge the semantic gap between the encoder’s shallow details and the decoder’s high-level semantics via an efficient cross-attention mechanism. Extensive experiments on the ISPRS Potsdam and Vaihingen datasets demonstrate that MAFMamba surpasses state-of-the-art Convolutional Neural Network (CNN), Transformer, and Mamba-based methods in terms of mIoU and mF1 scores. Notably, it achieves superior accuracy while maintaining linear computational complexity and low memory usage, underscoring its efficiency in complex remote sensing scenarios. Full article

Diplodia shoot blight is an opportunistic fungal pathogen infesting many conifer species and it has a global distribution. Depending on the duration and severity of the disease, affected needles appear yellow (chlorotic) for a brief period before becoming red or brown in colour. These symptoms can occur on individual branches or over the entire crown. Aerial sketch-mapping or the manual interpretation of aerial photography for tree health surveys are labour-intensive and subjective. Recently, however, the application of deep learning (DL) techniques to detect and classify tree crowns in high-spatial-resolution imagery has gained significant attention. This study evaluated two complementary DL approaches for the detection and classification of Pinus radiata trees infected with diplodia shoot blight across five geographically dispersed sites with varying topographies over two acquisition years: (1) object detection using YOLOv12 combined with Segment Anything Model (SAM) and (2) pixel-level semantic segmentation using U-Net, SegFormer, and EVitNet. The three damage classes for the object detection approach were ‘yellow’, ‘red-brown’ (both whole-crown discolouration) and ‘dead tops’ (partially discoloured crowns), while for the semantic segmentation the three classes were yellow, red-brown, and background. The YOLOv12m model achieved an overall mAP50 score of 0.766 and mAP50–95 of 0.447 across all three classes, with red-brown crowns demonstrating the highest detection accuracy (mAP50: 0.918, F1 score: 0.851). For semantic segmentation models, SegFormer showed the strongest performance (IoU of 0.662 for red-brown and 0.542 for yellow) but at the cost of longest training time, while EVitNet offered the most cost-effective solution achieving comparable accuracy to SegFormer but with a superior training efficiency with its lighter architecture. The accurate identification and symptom classification of crown damage symptoms support the calibration and validation of satellite-based monitoring systems and assist in the prioritisation of ground-based diagnosis or management interventions. Full article

The Balaton region is Hungary’s most important recreational area, known for Central Europe’s largest freshwater lake and its traditional vineyard and horticultural landscapes. Since 1990, vineyard and orchard abandonment and intensified shoreline urbanization have increasingly threatened both landscape character and ecological balance. This study analyses land-use changes in the Balaton hinterland and evaluates the effectiveness of regional land-use regulation between 1990 and 2018, with a focus on the 2000 Balaton Law (BKÜRT), which sought to preserve traditional land uses by permitting construction only where at least 80% of vineyard parcels remained cultivated. Spatial–temporal analysis was based on CORINE Land Cover (CLC) data from 1990 to 2018, supplemented by change layers from the Copernicus Land Monitoring Service. The CORINE Land Cover classification is a three-level hierarchical system (5 Level-1 groups, 15 Level-2 classes, and 44 Level-3 classes) developed by the EEA to provide standardized, satellite-based land cover information across Europe. Land cover was aggregated into major categories (using Level-1 and Level-2 classes) relevant to the Hungarian landscape. To address CLC limitations related to representing vineyards as relatively homogeneous units despite substantial differences in the density and scale of built structures, detailed case studies were conducted in three C1 vineyard zones—Alsóörs, Paloznak, and Szentantalfa—using historical aerial photographs, Google Earth imagery, and the Hungarian Ecosystem Map (NÖSZTÉP). Despite the restrictive regulatory framework, the CLC database showed that the share of vineyards in the vineyard regulation zone (C-1, C-2) decreased between 1990 and 2018 from 45.4% to 35.8% (the share of gardens and fruit plantations had changed from 9.7% to 15.5%). In the whole Balaton region, there was an approximately 18% decline in vineyard areas. Considering the M-2 horticultural zone, the garden coverage increased from 18.9% in 1990 (17.7% in 2000) to 30.5% (share of vineyards changed from 54.3% (54.6% in 2000) to 38.8%). At the regional level, gardens and fruit plantations had a smaller decrease (3.2%). Although overall trends were more favorable than at the national level, regulatory measures proved insufficient to prevent the conversion of vineyards and orchards in sensitive areas, particularly on slopes overlooking the lake, in proximity to tourist hubs, and in areas exposed to strong development pressure. By 2018, the C1 zone had expanded spatially but became less targeted, as the proportion of vineyards within it decreased. Boundary refinements failed to substantially improve regulatory precision or effectiveness. The case studies reveal a gradient of regulatory strictness reflecting differing landscape protection priorities and stages of vineyard transformation, with Alsóörs responding to long-standing, partly irreversible changes while attempting to slow further landscape alteration. To counter ongoing negative trends, more targeted and enforceable regulations are required, including a clearer separation of cultivated and recreational land uses, a maximum building size of 80 m² for recreational properties, and a reassessment of vineyard zone boundaries to better reflect active cultivation and protect sensitive landscapes. Full article

Photogrammetric reconstruction from indoor imagery requires either labor-intensive ground control points (GCPs) or positioning sensor integration. While global navigation satellite system technology revolutionized aerial photogrammetry by enabling direct georeferencing through integrated sensor orientation (ISO), indoor environments lack an equivalent positioning solution. Before indoor positioning systems can be adopted for photogrammetric applications, their fundamental measurement precision must be established. This study characterizes the repeatability and temporal stability of the ZeroKey Quantum real-time location system (RTLS) as a prerequisite to testing reconstruction accuracy when RTLS measurements provide camera pose constraints in photogrammetric bundle adjustment. Through systematic tripod-mounted observations across 30 test locations in a controlled laboratory environment, optimal data collection protocols were determined, temporal stability was investigated, and measurement precision was quantified. An automated position-based stationary detection algorithm using a 20 mm threshold successfully identified all 30 stationary periods for durations of 30 s or less. Optimal duration analysis revealed that 1 s observation windows achieve 3 mm position precision and 1° orientation precision after brief settling, enabling practical workflows with worst-case total collection time of 2.5 s per station. Per-axis uncertainties were quantified as 1.6 mm, 1.7 mm, and 1.1 mm root mean square (RMS) for position and 0.08°, 0.09°, and 0.07° RMS for orientation. These findings demonstrate that ultrasonic RTLS achieves millimeter-level position repeatability and sub-degree orientation repeatability, establishing the measurement precision necessary to justify subsequent accuracy testing through photogrammetric bundle adjustment. Full article

The Guizhou Plateau, with the most extensive and representative karst landforms worldwide, is characterized by severe soil erosion and a highly fragile ecological environment. However, large-scale assessments of soil conservation services in this region remain limited. A key challenge lies in identifying appropriate datasets and methodologies for regional-scale soil conservation service evaluations, particularly under conditions of data scarcity or limited data accuracy. In this study, Unmanned Aerial Vehicle imagery, runoff plot observations, ground survey data, and multi-source satellite remote sensing data were integrated to refine LS and C in the Revised Universal Soil Loss Equation (RUSLE), thereby establishing a parameterized and localized soil erosion model. This improvement provided a methodological foundation for soil conservation service research in the region. Subsequently, the spatiotemporal variations in soil conservation services in the Guizhou Plateau over the past two decades were assessed. Furthermore, the relationships between soil conservation services and other key ecosystem services, including water conservation and carbon sequestration, were quantitatively examined, and the driving factors were analyzed. Soil conservation on the Guizhou Plateau exhibited an improving trend from 2000 to 2020. In karst areas, the relationship between soil conservation and water conservation was primarily influenced by temperature, altitude, and vegetation coverage, whereas in non-karst areas, it was regulated by rainfall and slope. Ecological restoration projects have enhanced the synergy between soil conservation and carbon sequestration by promoting vegetation cover. These findings could contribute to the next stage of ecological engineering initiatives and ecological policy implementation in Guizhou. Full article

Driven by dangerous Santa Ana winds and fueled by dry vegetation, the 2025 Eaton and Palisades wildfires in California caused historic levels of devastation, ultimately becoming the second and third most destructive fires in California history. Burning at the same time and drawing from the same resources, these fires burned a combined total of 16,251 structures. The first several hours of an emerging wildfire are a crucial period for fire officials to assess potential damage and develop a timely and appropriate response. A method to quickly generate accurate estimates of structural damage is essential to providing this crucial rapid response to wildfires. In this paper, we present a machine learning approach for automated assessment of structural damage caused by wildfires. By leveraging multiple data sources in model development (satellite-based building footprints, expert-labeled post-fire damage points, fire perimeters, and aerial thermal imagery) and innovative data processing techniques, the approach can be used to identify various levels of structural damage from just aerial thermal imagery during operational use. The resulting system offers an effective approach for rapid and reliable assessment of burned structures, suitable for operational wildfire damage assessment. Results on the Eaton and Palisades Fires demonstrate the effectiveness of this method and its applicability to real-world scenarios. Full article

Coastal landscapes are complex socio-ecological systems that undergo rapid transformations driven by both natural dynamics and human pressures. Their sustainable management depends on robust, cost-effective remote sensing methodologies for long-term monitoring and quantitative assessment of spatiotemporal change. In this study, we developed an integrated remote-sensing-based framework that combines historical aerial photograph interpretation, transition matrix analysis, and machine learning to assess coastal dune landscape dynamics over a seventy-year period. Georeferenced orthorectified and preprocessed aerial imagery freely available from the Italian Ministry of the Environment for the years 1954, 1986, and Google Satellite Images for 2022 were used to generate detailed land-cover maps, enabling the analysis of two temporal intervals (1954–1986 and 1986–2022). Transition matrices quantified land-cover conversions and identified sixteen dynamic processes, while a Random Forest (RF) classifier, optimized through parameter tuning and cross-validation, modeled and compared landscape dynamics within protected Long-Term Ecological Research (LTER) sites and adjacent unprotected areas. Model performance was evaluated using Balanced Accuracy (BA) to ensure robustness and to interpret the relative importance of change-driving variables. The RF model achieved high accuracy in distinguishing change processes inside and outside LTER sites, effectively capturing subtle yet ecologically relevant transitions. Results reveal non-random, contrasting landscape trajectories between management regimes: protected sites tend toward naturalization, whereas unprotected sites exhibit persistent urban influence. Overall, this research demonstrates the potential of integrating multi-temporal remote sensing, spatial statistics, and machine learning as a scalable and transferable framework for long-term coastal landscape monitoring and conservation planning. Full article

This study presents a detailed analysis of the morphological evolution of beaches in the Bocagrande sector of Cartagena de Indias, Colombia, over more than a decade, based on periodic monitoring of six beach profiles. The beaches in this area are in bays constrained by headlands and promontories located at both ends of each bay. Changes in shoreline position, dry beach widths, and the surf zone were evaluated using aerial photographs, orthophotos, satellite imagery, and field data, together with sediment size determined through granulometric analysis. The results indicate that the beaches exhibit characteristics of wave-dominated, exposed systems, with sediments classified as fine sand that tend to increase in grain size toward the northern sector of the bay. A cyclical variation in the shoreline was observed, with average retreats and advances ranging from 5 to 10 m, depending on the climatic season. Dry beach widths ranged from 10 to 90 m, decreasing toward the north. Differences in morphology between profiles and shoreline variation are attributed to the climatic season, profile location within the bay, and proximity to a coastal structure and its particular type. Beach profiles were fitted to conceptual equilibrium profile models using traditional equations, which yielded a coefficient of determination of 0.76; when machine learning algorithms were applied, this value improved to 0.99. This study provides an important baseline for future morphological assessments and coastal management efforts in the city and places with similar characteristics, particularly considering ongoing shoreline protection projects. Full article

This study proposes a “zonal inversion–fusion mosaicking” technical framework to address the challenge of acquiring continuous full-profile topography data in coastal wetland intertidal zones. The framework integrates and synergistically analyzes data from multi-platform sensors, including satellite, unmanned aerial vehicle (UAV), and ground-based instruments. Applied to the Min River Estuary wetland, this framework employs zone-specific optimization strategies: in the inundated zone, the topography was inverted using Landsat-9 OLI imagery and a Random Forest algorithm (R² = 0.79, RMSE = 2.08 m); in the bare flat zone, a linear model was developed based on Sentinel-2 time-series imagery using the inundation frequency method, and it achieved an accuracy of R² = 0.86 and RMSE = 0.34 m; and in the vegetated zone, high-precision topography was derived from UAV oblique photography with Kriging interpolation (RMSE = 0.10 m). The key innovation is the successful generation of a seamless full-profile digital elevation model (DEM) with an overall RMSE of 0.54 m through benchmark unification and precision-weighted fusion algorithms from the sensor data fusion perspective. This study demonstrates that the synergistic sensors framework effectively overcomes the limitations of single-sensor observations, providing a reliable and generalizable integrated solution for the full-profile topographic monitoring of tidal flats, which offers crucial support for coastal wetland research and management. Full article

Wildfire-induced disturbances to soil and vegetation can significantly impact streamflows for years, depending upon the degree of burn severity. Accurately predicting the effects of wildfire on streamflow at the watershed scale is essential for effective water budget management. This study presents a novel approach to generating a burn severity map on a small scale by integrating unmanned aerial vehicle (UAV)-based thermal imagery with Landsat-derived Differenced Normalized Burn Ratio (dNBR) and upscaling burned severity to the entire burned area. The approach was applied to the Thompson Ridge Fire perimeter, and the upscaled UAV-Landsat-based burn severity map achieved an overall accuracy of ~73% and a kappa coefficient of ~0.62 when compared with the Burned Area Emergency Response’s (BAER) fire product as a reference map, indicating moderate accuracy. We then tested the transferability of burn severity information to a Beaver River watershed by applying Random Forest models. Predictors included topography, spectral bands, vegetation indices, fuel, land cover, fire information, and soil properties. We calibrated and validated the Distributed Hydrology Soil Vegetation Model (DHSVM) against observed streamflow and Snow Water Equivalent (SWE) data within the Beaver River watershed and measured model performance using Nash–Sutcliffe Efficiency (NSE), Kling–Gupta Efficiency (KGE), and Percent Bias (PBIAS) metrics. We adjusted soil (maximum infiltration rate) and vegetation (fractional vegetation cover, snow interception efficiency, and leaf area index) parameters for the post-fire model setup and simulated streamflow for the post-fire years without vegetation regrowth. Streamflow simulations using the upscaled and transferred UAV-Landsat burn severity map and the Burned Area Emergency Response’s (BAER) fire product produced similar post-fire hydrologic responses, with annual average flows increasing under both approaches and the UAV-Landsat-based simulation yielding slightly lower values, by less than 6% compared to the BAER-based simulation. Our results demonstrate that the UAV-satellite integration method offers a cost- and time-effective method for generating a burn severity map, and when combined with the transferability method and hydrologic modeling, it provides a practical framework for predicting post-fire streamflow in both burned and unburned watersheds. Full article

The pine wood nematode (PWN), one of the globally significant forest diseases, has driven the demand for precise detection methods. Recent advances in satellite remote sensing technology, particularly ultra-high-resolution optical imagery, have opened new avenues for identifying PWN-infected trees. In order to systematically evaluate the ability of ultra-high-resolution optical remote sensing and the influence of spatial and spectral resolution in detecting PWN-infected trees, this study utilized a U-Net network model to identify PWN-infected trees using three remote sensing datasets of the ultra-high-resolution multispectral imagery from Beijing 3 International Cooperative Remote Sensing Satellite (BJ3N), with a panchromatic band spatial resolution of 0.3 m and six multispectral bands at 1.2 m; the high-resolution multispectral imagery from the Beijing 3A satellite (BJ3A), with a panchromatic band resolution of 0.5 m and four multispectral bands at 2 m; and unmanned aerial vehicle (UAV) imagery with five multispectral bands at 0.07 m. Comparison of the identification results demonstrated that (1) UAV multispectral imagery with 0.07 m spatial resolution achieved the highest accuracy, with an F1 score of 89.1%. Next is the fused ultra-high-resolution BJ3N satellite imagery at 0.3 m, with an F1 score of 88.9%. In contrast, BJ3A imagery with a raw spatial resolution of 2 m performed poorly, with an F1 score of only 28%. These results underscore that finer spatial resolution in remote sensing imagery directly enhances the ability to detect subtle canopy changes indicative of PWN infestation. (2) For UAV, BJ3N, and BJ3A imagery, the identification accuracy for PWN-infected trees showed no significant differences across various band combinations at equivalent spatial resolutions. This indicates that spectral resolution plays a secondary role to spatial resolution in detecting PWN-infected trees using ultra-high-resolution optical imagery. (3) The 0.3 m BJ3N satellite imagery exhibits low false-detection and omission rates, with F1 scores comparable to higher-resolution UAV imagery. This indicates that a spatial resolution of 0.3 m is sufficient for identifying PWN-infected trees and is approaching a point of saturation in a subtropical mountain monsoon climate zone. In conclusion, ultra-high-resolution satellite remote sensing, characterized by frequent data revisit cycles, broad spatial coverage, and balanced spatial-spectral performance, provides an optimal remote sensing data source for identifying PWN-infected trees. As such, it is poised to become a cornerstone of future research and practical applications in detecting and managing PWN infestations globally. Full article

Mountain glaciers are sensitive indicators of climate variability, and their retreat since the end of the Little Ice Age (LIA) has strongly reshaped alpine environments worldwide. In the Greater Caucasus, glacier shrinkage has accelerated over the past century, yet detailed multi-temporal reconstructions remain limited for many glaciers. Here, we reconstruct the post-LIA evolution of Tsaneri–Nageba Glacier, one of largest ice bodies in the Georgian Caucasus, and document the development of its newly formed proglacial lake. Using a combination of geomorphological mapping, historical maps, multi-temporal satellite imagery, Uncrewed Aerial Vehicle (UAV) photogrammetry, and sonar bathymetry, we quantify glacier change from ~1820 to 2025 and provide the first direct measurements of a proglacial lake in the Tsaneri–Nageba system—and indeed in the Georgian Caucasus as a whole. Our results reveal that Tsaneri–Nageba Glacier has shrunk from ~48 km² at its LIA maximum to ~30.6 km² in 2025, a loss of −43.5% (or −0.21% yr⁻¹). The pace of shrinkage intensified after 2000, with the steepest losses recorded between 2014 and 2025. Terminus positions shifted up-valley by nearly 3.9 km (Tsaneri) and 4.3 km (Nageba), accompanied by fragmentation of the former compound valley glacier into smaller ice bodies. Long-term meteorological records confirm strong climatic forcing, with pronounced summer warming since the 1990s and declining winter precipitation. A proglacial lake started to form in mid-summer 2015, which by 03/09/15 had a surface area of ~14,366 m², expanding to ~106,945 m² by 10/07/2025. The lake is in contact with glacier ice and is thus prone to calving. It is dammed by unconsolidated moraines and bounded by steep, active slopes, making it susceptible to generating a glacial lake outburst flood (GLOF). By providing the first quantitative measurements of a proglacial lake in the region, this study establishes a baseline for future monitoring and risk assessment. The findings highlight the urgency of integrating glaciological, geomorphological, and hazard studies to support community safety and water resource planning in the Caucasus. Full article