Search Results (9,695)

Remote sensing-based mapping of crop planting structures in irrigation districts plays a vital role in forecasting regional production and optimizing water resource allocation. However, optical satellite imagery is limited by insufficient spatial resolution when applied to fragmented farmland landscapes, while unmanned aerial vehicle (UAV) imagery is limited by spatial coverage and high data processing costs. To address these bottlenecks, this study proposed a cross-scale collaborative extraction framework utilizing the CycleGAN network and transfer learning to map summer harvest crops (winter wheat and rapeseed) in the Baojixia Irrigation District for the year 2023. First, multiple semantic segmentation models—including U-Net, DeepLabv3+, SegFormer, and HRNet—were evaluated on a joint satellite–UAV dataset, with U-Net selected as the optimal backbone. Next, CycleGAN was introduced to perform style translation from the UAV domain to the satellite domain. This step generated high-fidelity, satellite-like images that preserve UAV-derived high-resolution spatial details, which were subsequently used to pre-train the U-Net backbone, significantly reducing the labor of manual annotation. Finally, the model was fine-tuned with real satellite images to achieve precise crop extraction. Results indicated that this framework accelerates model convergence and improves segmentation accuracy. The proposed method achieved an mIoU of 85.09%, an mPA (Recall) of 91.63%, a Precision of 91.97%, an Accuracy of 93.57%, and an F1-Score of 91.80%, outperforming the baseline U-Net model by 2.98%, 2.00%, 1.66%, 1.52%, and 1.83%, respectively. By successfully transferring high-resolution prior knowledge into the satellite feature space, this study provides a cost-effective and highly accurate solution for crop identification in complex agricultural landscapes, breaking the spatial limitations of UAV remote sensing. Full article

Artificial satellite trails are becoming an increasingly important challenge for ground-based telescopes, as they affect the quality of the observations needed for scientific analysis. In this work, we present a machine learning approach based on a wavelet-transform encoder whose features are used as input to a Random Forest binary classifier that detects the presence of trails in astronomical images. Using both real and simulated data, the method achieves an accuracy of 0.9721 with a low false-positive rate (0.0070), which is crucial for subsequent operational analysis and for addressing space debris in Earth’s orbit. This approach not only enables the automation of the analysis, considering the large datasets involved, but also provides a robust technique that leverages the benefits of the 2-level wavelet decomposition of the input images. Full article

Remote sensing research increasingly relies on heterogeneous satellite, UAV, hyperspectral, multispectral, SAR, and environmental monitoring data to support land, urban, hydrological, and environmental applications. However, these data are often affected by sensor differences, spatial and temporal heterogeneity, missing observations, irregular sampling, noise, and non-stationary environmental processes. This systematic review was conducted within the context of the Romanian Hub for Artificial Intelligence (HRIA) project, which supports the development of strategic artificial intelligence technologies. The review synthesizes current research on adaptive neural networks for remote sensing and Earth observation, with particular attention to Liquid Neural Networks and related continuous-time neural models. A systematic search was conducted across IEEE Xplore, Scopus, Web of Science, ScienceDirect, SpringerLink, Wiley Online Library, Google Scholar, and reference lists. After duplicate removal, screening, and full-text assessment, 61 studies published between 2018 and 2026 were included in the qualitative synthesis. The findings show that adaptive neural networks have gained increasing attention after 2022 and are mainly applied to image-centered remote sensing tasks, including classification, mapping, object detection, segmentation, enhancement, and change detection. Most studies adapt established deep learning architectures through multi-scale processing, adaptive feature fusion, attention mechanisms, graph relationships, or task-specific refinement. Continuous-time models are used less frequently but are relevant for irregular observations and dynamic environmental processes. Liquid Neural Networks remain emerging, and current evidence suggests only preliminary, task-specific relevance for irregular, noisy, multimodal, and dynamic remote sensing applications. Full article

Accurate stereo visual–inertial measurement is essential for mobile robots operating in Global Navigation Satellite System (GNSS)-denied and structurally complex environments. In stereo visual–inertial odometry (VIO), pose and trajectory outputs depend strongly on the point measurements delivered by the visual front end before sensor-fusion update. In sparse-texture but structurally regular scenes, tracked point features may exhibit poor persistence, uneven spatial distribution, and local tracking noise, even when informative line structures are present. Existing point–line VIO methods can improve positioning accuracy by introducing line landmarks or line residuals, but they usually modify the estimator state, measurement model, and Jacobian treatment. We present a scene-adaptive line-aware visual measurement conditioning method for stereo VIO front ends with point-measurement updates. The method uses 2-D image-line segments as lightweight structural priors and applies bounded normal-direction conditioning to reliable point measurements before a fixed-interface VIO back-end update. A sparse pruning safeguard removes only highly inconsistent long-lived tracks under strong structural support, while a scene-level confidence gate attenuates the intervention when line evidence is weak or unstable. The method is instantiated and evaluated in an S-MSCKF pipeline. On the reported EuRoC MAV sequences, it reduces the sequence-averaged absolute trajectory error (ATE) RMSE by approximately 13% relative to S-MSCKF, with 3–27% reductions on machine-hall sequences. On three real-world robot measurement sequences with an RTK-aided inertial reference, the mean Sim(2)-aligned planar position error decreases from 8.72 m to 7.31 m, and the mean yaw error decreases from $8.{02}^{\circ }$ to $6.{76}^{\circ }$; an additional scale-preserving SE(2) evaluation reveals sequence-dependent planar behavior and residual metric-scale sensitivity. Candidate-level stereo-consistency diagnostics show subpixel mean and 95th-percentile image-domain perturbations without systematic vertical-stereo bias, while the final reliability-weighted primary-view update is analytically bounded by approximately 0.221 pixels in the reported implementation. Runtime profiling reports an average front-end time of 33.34 ms on the tested CPU platform, close to the 33.3 ms frame period of the 30 Hz stereo input, although the $\mu +3\sigma$ runtime of 47.23 ms exceeds a strict frame-by-frame 30 Hz budget. These results suggest that line-aware front-end conditioning can improve visual measurement quality in structured stereo visual–inertial sensing without modifying the evaluated back-end interface. Full article

Floating plastic debris in urban canals is a management-relevant precursor to downstream microplastic pollution. This structured narrative review synthesizes conventional field surveys, camera-, UAV-, and satellite-based image analysis and AI-assisted image-based monitoring. Emphasis is placed on Southeast Asian engineered canals, where monsoon-driven flow, tides, gates, turbidity, glare, occlusion, and organic debris challenge continuous observation. Conventional surveys provide verifiable composition data but limited temporal coverage. Camera systems increase observation frequency, while deep learning can automate detection and tracking; however, reported performance depends strongly on the dataset, site, target size, and validation design. Published studies show substantial losses under cross-site transfer and condition-specific gains from preprocessing rather than a universal accuracy threshold. The synthesis therefore develops a decision-oriented framework linking camera calibration, conditional preprocessing, site-separated validation, uncertainty reporting, and hydrological data to operational triggers for cleanup or interception. Current evidence supports monitoring and pilot decision support, while broader autonomous operation requires further field validation. Priorities include transparent evidence reporting, shared Southeast Asian datasets, standardized metrics and environmental descriptors, cross-site testing, and life-cycle evaluation of deployment cost and maintenance. Full article

Micro-vibrations of satellite platforms can reduce the pointing accuracy of space optical communication links, leading to a reduction in link margin and even link interruption. Traditional methods rely on accelerometers to obtain vibration labels, leading to hardware deployment difficulties and additional energy overhead in space or power constrained scenarios. Here, we propose a physics-encoded self-supervised vibration sensing model that directly recovers vibration signals from time-series images of the lunar surface without external sensors. The model consists of an optical flow module, a convolutional network, and a memory network, formulating vibration sensing as a physical inversion problem constrained by an image reconstruction process. This approach extracts the textural features of the lunar surface and the temporal dynamics characteristics of platform vibrations, achieving end-to-end high-precision vibration sensing. In simulation experiments, it attains excellent performance, with a coefficient of determination ($R^2$) of 0.9975, a mean absolute error (MAE) of 0.0727, and a root mean square error (RMSE) of 0.0821. Furthermore, experiments on a real vibration platform validate the engineering applicability of the model, achieving an $R^2$ of 0.9910, an MAE of 0.1180, and an RMSE of 0.1463, with predicted values closely matching the ground truth. The proposed model exhibits sub-pixel-level accuracy and excellent generalization capability in both simulated and real-world experimental scenarios, providing an effective solution for visual sensing of micro-vibrations on satellite platforms in space optical communication. Full article

High-resolution (HR) Ground Control Point (GCP) chips are essential for accurate satellite image registration, yet their generation commonly relies on aerial imagery, which is often limited by data availability and update frequency. To improve the usability of satellite-derived GCP chips as an alternative, this study systematically investigates the influence of deep learning-based image super-resolution (SR) on GCP chip template matching under varying input spatial resolution conditions. GCP chips extracted from KOMPSAT-3 imagery were synthetically degraded using ×4 and ×2 downsampling, while original-resolution chips (×1) were also included for comparison. The degraded chips were enhanced using SR models and matched to KOMPSAT-3A imagery using both conventional and deep learning-based template matching methods. The experimental results show that SR is more effective for input GCP chips with limited spatial detail, with the largest improvements obtained under the ×4 downsampling condition (~2.8 m GSD). The contribution of SR is further influenced by geometric resampling during template matching and by the adopted matching method. These findings identify the conditions under which SR provides meaningful improvements and offer practical guidance for enhancing satellite-derived GCP chips, extending their usability for satellite image registration when aerial imagery is unavailable or requires frequent updates. Full article

Hyperspectral retrieval of nitrogen-related vegetation variables has undergone rapid methodological advances driven by the emergence of protein-sensitive radiative transfer models (RTMs), modern machine learning (ML), and operational imaging spectroscopy. This review synthesizes recent developments in hyperspectral retrieval of nitrogen-related vegetation variables across leaf and canopy scales, with particular emphasis on advances reported between 2020 and 2026. We examine the evolution from classical parametric regression and nonlinear ML approaches towards physically based RTM inversion and hybrid RTM–ML frameworks that integrate the complementary strengths of physical modeling and statistical learning. Particular attention is given to protein-sensitive RTMs, advanced ML approaches, and uncertainty-aware retrieval. Recent developments highlight the potential of hybrid RTM–ML frameworks to combine physical consistency with computationally efficient statistical learning, while probabilistic methods such as Gaussian Process Regression provide additional capabilities for uncertainty characterization. The review further discusses the transition from experimental studies to operational applications enabled by airborne and satellite imaging spectroscopy, including PRISMA, EnMAP, and forthcoming missions such as CHIME. Remaining challenges include the inherently ill-posed nature of nitrogen retrieval, limited and insufficiently representative calibration data, uncertainty characterization, and generalization across sensors, species, and ecosystems. Overall, the reviewed evidence points towards increasingly integrated retrieval frameworks, while emphasizing that robust transferability and operational implementation remain dependent on representative data, physical realism, and rigorous uncertainty assessment. Full article

Fluvial sand bodies represent one of the most significant reservoir types in hydrocarbon exploration. Restricted by climatic conditions, sedimentary environments and the properties of provenance parent rocks, sedimentary characteristics and sand-body architectures exhibit substantial spatial variations across different river systems and along individual river segments. Research on modern sedimentary processes of the Weihe River provides critical insights for advancing continental fluvial sedimentology theories and reconstructing paleoriver sedimentary models for analogous basins. Integrating high-resolution satellite image interpretation combined with systematic field geological surveys across typical river reaches, this study systematically characterizes the spatial differentiation of river patterns, sedimentary signatures, sand-body architectures and their primary controlling factors within the Weihe Basin. The results reveal a distinct three-segment spatial differentiation pattern of fluvial styles in the Weihe Basin: braided rivers dominate the Baoji–Zhouzhi reach; low-sinuosity meandering rivers occur in the reach from Zhouzhi to Lintong; and high-sinuosity meandering rivers prevail in the downstream segments below Lintong. Unique hydrodynamic regimes associated with each river type control sedimentary partitioning and sand-body development. Braided rivers feature intense hydrodynamic force and coarse-grained sediments, with sedimentary assemblages consisting of gravelly channel deposits, mid-channel bars and floodplain deposits, which form thick stacked sand bodies via multi-stage sedimentary superimposition. Low-sinuosity meandering rivers possess moderate hydrodynamic energy and are dominated by sandy-gravel deposits, yielding a complete sedimentary succession composed of channel fills, point bars, natural levees and floodplains. High-sinuosity meandering rivers are characterized by weak hydrodynamic conditions and fine grain sizes dominated by sandstone and mudstone units, developing diverse sedimentary facies including channels, crevasse splays and oxbow lake deposits. The spatial heterogeneity of the sedimentary system across the Weihe Basin is synergistically controlled by the channel gradient, provenance attributes, sediment grain size and sediment concentration. This study clarifies the sedimentary evolutionary laws of modern rivers under semi-arid and semi-humid climatic conditions, enriches fundamental fluvial sedimentology theories, and supplies a modern sedimentary analog for paleoriver identification, paleoenvironmental reconstruction and hydrocarbon exploration targeting fluvial reservoir systems. Full article

The development of temporally consistent long-term normalized difference vegetation index (NDVI)climate data records is essential for global change and ecosystem research. The Medium Resolution Spectral Imager-II (MERSI-II) sensor aboard China’s Fengyun-3D (FY-3D) satellite shares similar spectral characteristics with Moderate Resolution Imaging Spectroradiometer (MODIS), offering potential for synergistic applications. However, systematic biases arising from differences in sensor design, radiometric calibration, and atmospheric correction hinder their direct combination. This study established a full-chain framework that integrated cross-calibration of surface reflectance using quasi-synchronous FY-3D/MODIS observations and a MERSI-II-specific atmospheric correction scheme based on the 6S radiative transfer model. After correction, the FY-3D NDVI shows substantially improved consistency with MODIS, achieving a reduction in root mean square error of over 25.9%, an increase in correlation coefficient of approximately 5%, and a decrease in mean absolute error of about 40%. Spatial biases are within ±0.1 over most global land areas, with robust performance across vegetation types and climate zones. Based on this technical framework, a fused FY-3D and MODIS NDVI climate data record was established, which has been operationalized at the Beijing Climate Center for global vegetation monitoring. This work provides a transferable framework for integrating Chinese Fengyun satellite data with international datasets like MODIS/VIIRS. Full article

Rivers and riparian zones support a variety of woody plant species and play an important role in riverine ecosystems and fluvial processes. Rapid establishment of herbaceous and woody vegetation occurs in unvegetated river channels, mainly because of dam construction and hydrological alterations. However, repeated monitoring of the three-dimensional structure over broad river corridors remains challenging. We aimed to assess the applicability of RGB-derived canopy-height models (CHMs) inferred using Depth Anything V2 for monitoring riparian woody vegetation. A monocular depth-estimation framework was trained using the National Agriculture Imagery Program-CHM dataset and applied to three Korean riverine environments. The inferred CHMs were evaluated against the LiDAR-derived CHMs and further tested using two application-oriented assessments: individual tree detection (ITD) and woody vegetation area classification. The RGB-derived CHMs reproduced the overall spatial patterns of the riparian canopy height, although the accuracy varied with vegetation structure and image acquisition conditions. The mean absolute error between RGB- and LiDAR-derived CHMs was approximately 0.96 m across the study sites. In the ITD assessment, the RGB-derived CHM achieved an F1 score of 0.73, compared with 0.80 for the LiDAR-derived CHM. For woody vegetation area classification, the RGB-derived CHM showed high pixel-level accuracy, while Dice coefficient and IoU varied depending on the canopy-height threshold and study site. These results suggest that the RGB-derived CHMs can serve as supplementary data for monitoring riparian woody vegetation when LiDAR acquisition is limited. Full article

Disaster response often requires evidence from several sources, including satellite imagery, social media, news reports, audio and video recordings, and event metadata. Existing disaster datasets, however, usually focus on one source, a limited set of modalities or a single task. This separation makes it difficult to evaluate models that must combine regional observations with ground-level evidence for the same disaster context. We introduce DisasterScope, an event-centric multimodal dataset and benchmark for disaster-type recognition, severity assessment and evidence retrieval. DisasterScope organizes satellite observations, social images, synchronized audio–video segments, observation text, report passages, and provenance metadata around canonical events. Its primary benchmark contains 12,159 fixed event-context bundles from 24 events and nine disaster classes. The dynamic-media inventory includes 273 source videos, 628 curated audio–video segments, 9.02 h of material and 5473 temporal windows. Labels are harmonized through source-label inheritance, taxonomy mapping, teacher assistance and partition-specific human review. Validation and test annotations were reviewed in full, while training annotations were sampled for review and accepted through a threshold gate. The benchmark evaluates full-input and unavailable-view conditions on the same bundle identities, allowing direct measurement of how each view affects a model without changing the evaluated sample population. DisasterScope therefore provides a traceable setting for studying multimodal disaster assessment across different disasters, evidence sources and input-availability conditions. Full article

High-resolution optical satellite constellations continuously generate massive volumes of remote sensing imagery, making automatic, ground-control-point-free (GCP-free) geometric positioning accuracy assessment increasingly important for ensuring the quality of downstream applications. However, conventional GCP-free inspection methods based on local feature matching often exhibit limited robustness under large initial positioning errors, weak-texture regions, cloud contamination, and temporal appearance variations, resulting in poor generalization across large-scale production scenarios. To address these challenges, this paper proposes a geometry-constrained framework that integrates Rational Polynomial Coefficient (RPC) prior constraints, coarse-to-fine registration, adaptive match-density-based block selection, hierarchical geometric verification, and a geolocation residual confidence measure into a unified automatic quality inspection pipeline. The framework leverages LoFTR for dense feature matching, but its principal contribution lies in the system-level integration and operational design for large-scale industrial satellite image production. Extensive experiments on multi-satellite and multi-scene datasets from the Jilin-1 satellite series show that the proposed method achieves a median positioning error below 2 m, an Average Precision (AP) improvement of 0.53 over the baseline, and nearly perfect accuracy on the evaluated test set for confidence thresholds above 0.5. The framework has also been deployed in the operational production system of multiple commercial Jilin-1 missions for more than six months, demonstrating its effectiveness, robustness, scalability, and practical applicability for large-scale optical satellite imagery. Full article

In densely vegetated and topographically complex mountainous areas, the applicability of SAR data for potential landslide hazard identification depends not only on whether slopes are visible to the radar, but also on whether stable interferometric coherence can be preserved under vegetation and terrain constraints. To clarify the applicability differences between L-band Lutan-1 and C-band Sentinel-1 in such environments, this study focused on Hanyuan County, Sichuan Province, China. Ascending and descending SAR images acquired by the two satellite systems from 2024 to 2025 were processed using stacking-based Interferometric Synthetic Aperture Radar (Stacking-InSAR) and Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) to extract regional deformation anomalies and time-series deformation characteristics of representative landslides. DEM, LiDAR, optical imagery, fractional vegetation cover (FVC) derived from Sentinel-2, and field investigation data were further integrated to establish a comparative framework linking geometric visibility, interferometric coherence, and landslide identification results. The results show that both Lutan-1 and Sentinel-1 provided favorable geometric observation conditions after combining ascending and descending tracks, with joint visibility proportions of 98.48% and 97.76%, respectively, indicating limited differences in geometric coverage within the study area. However, at a unified grid scale, the mean coherence and valid grid-cell proportion of Lutan-1 reached 0.564 and 72.49%, respectively, substantially higher than those of Sentinel-1, which were 0.320 and 24.26%. As FVC increased, coherence decreased for both datasets, but Lutan-1 maintained higher coherence in densely vegetated areas, suggesting stronger adaptability to vegetation-induced decorrelation. Based on integrated interpretation of multi-source remote sensing data, 77 potential landslide hazards were identified in the study area, including 74 detected by Lutan-1, 17 detected by Sentinel-1, and 14 jointly detected by both datasets. Comparisons of representative landslides further show that Lutan-1 provided a higher density of valid deformation points in densely vegetated and small-scale landslides, with deformation patterns corresponding well to slope geomorphic boundaries and local deformation zones. Sentinel-1, with its higher temporal sampling density, can provide complementary information for time-series verification and multi-source cross-validation of key landslides. These results indicate that Lutan-1 is more suitable for spatial identification of potential landslide hazards in densely vegetated, topographically complex mountainous areas, while the joint use of Lutan-1 and Sentinel-1 can better balance landslide identification detail and time-series monitoring continuity. Full article

Strong and optically conspicuous frontal boundaries are common in the river-dominated Louisiana–Texas Shelf (LTS). Variable wind stress forcing along cross-shelf density gradients results in convergences/divergences that may lead to rapid vertical water mass displacements. In cases where near-bottom shelf waters are displaced to the surface, the associated optical anomaly is often distinct in satellite ocean color data. A satellite-observed optical feature consistent with near-bottom-water ventilation is examined over the LTS with multiple satellite-based ocean color radiometers (OLCI, VIIRS), as well as data from the Advanced Baseline Imager (ABI) on the geostationary GOES-R platform. In the aftermath of an atmospheric cold front passage and sustained northerly winds, the combined satellite analysis reveals a rapidly westward moving optical front delineated by a sharp visible-band reflectivity gradient. Ocean model simulations reproduce a qualitatively similar displacement of surface density fields that is consistent with advection by the along-front current with a potentially modulating influence from the diurnal heating. This study serves as an example of the kind of analyses that may be possible from future geostationary ocean color missions. Full article