IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献

{"title":"Wind-Concerned Sea Ice Detection and Concentration Retrieval From GNSS-R Data Using a Modified Convolutional Neural Network","authors":"Wei Ban;Linhu Zhang;Xiaohong Zhang;Han Nie;Xiaoli Chen;Xuejing Chen","doi":"10.1109/JSTARS.2025.3549383","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549383","url":null,"abstract":"Spaceborne global navigation satellite system reflectometry method has been increasingly utilized for sea ice parameters retrieval. The coupling effects between wind speed and retrieval parameters was not considered in both traditional threshold-based methods and neural network models. To address this, a wind-concerned convolutional neural network (WCNN) model for sea ice detection and concentration retrieval is proposed. The model is based on convolutional layers for the feature extraction from delay-Doppler maps, along with fully connected layers for fusing the flattened feature map and wind speed parameters. After data training and testing, the WCNN model achieved sea ice concentration (SIC) retrieval accuracies with RMSE values of 8.61% in the Antarctic and 11.70% in the Arctic, with correlation coefficients of 0.97 in both regions. The sea ice detection accuracy reached 98.19% and 97.08%, respectively. In summary, the comparison of WCNN SIC retrieval performance across varying wind speeds demonstrates that incorporating wind speed data into the WCNN model significantly reduces the misclassification of seawater as sea ice in low wind conditions (0–10 m/s) and lowers the misclassification of sea ice as seawater in high wind conditions (10–20 m/s). Furthermore, the spatiotemporal distribution characteristics of the retrieval results, the advantages and weaknesses of the model are discussed.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"9755-9763"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10918841","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MS3OSD: A Novel Deep Learning Approach for Oil Spills Detection Using Optical Satellite Multisensor Spatial-Spectral Fusion Images","authors":"Kai Du;Yi Ma;Zhongwei Li;Rongjie Liu;Zongchen Jiang;Junfang Yang","doi":"10.1109/JSTARS.2025.3550421","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550421","url":null,"abstract":"Marine oil spills pose a significant threat to ecosystems, highlighting the critical need for effective monitoring technology. Optical remote sensing technology plays a crucial role in monitoring marine oil spills. However, its performance is constrained by inherent tradeoffs among temporal, spatial, and spectral resolutions, making it difficult for a single sensor to fully meet the demands of oil spill monitoring. Furthermore, existing oil spill detection algorithms often prioritize surrounding spatial features while neglecting the contribution of central spectral features, resulting in reduced detection accuracy. To address these issues, this article proposes a joint framework for multisensor data spatial-spectral fusion and oil spill detection. This framework fuse images from the coastal zone imager (50 m, 4 bands) with images from the ultraviolet imager and the Chinese Ocean Color and Temperature Scanner (1000 m, 10 bands), all of which are onboard Haiyang-1C/D satellites, generating high temporal and spatial resolution ultraviolet-visible-near-infrared range images with 10 bands. The framework uses parallel branches, including a convolutional neural network and a vision transformer, to extract surrounding spatial features and central spectral features from the fused data. This design enables the effective combination of fine-grained spatial information with multiband spectral information, facilitating precise detection of oil spills in various emulsification states under different sun glint conditions. The proposed framework demonstrates strong performance, achieving F1-scores of 95.24% and 93.04% for detecting oil slicks and oil emulsions under weak sun glint conditions, and 90.06% for positive contrast oil spills under strong sun glint conditions. This study provides new insights for advancing oil spill monitoring and highlights the potential of multisensor data fusion in marine target detection.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8617-8629"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10921724","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combination Manner of Sampling Method and Model Structure: The Key Factor for Rice Mapping Based on Sentinel-1 Images Using Data-Driven Machine Learning","authors":"Pengliang Wei;Jiao Guo;Jiaqian Lian;Chaoyang Wang","doi":"10.1109/JSTARS.2025.3550109","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550109","url":null,"abstract":"Agricultural remote sensing community is increasingly focusing on enhancing crop mapping accuracy by improving data-driven machine-learning model structures, yet ignoring impact of sampling–model structure combination on it, which may prevent full utilization of input data, especially for synthetic aperture radar images with fewer crop prior features. Consequently, this article took rice as target crop, and systematically performed rice mapping experiments based on Sentinel-1 images to assess mapping accuracies, model learning results, and model uncertainty under different sampling–model structures combinations. The sampling methods included pixel sampling in buffer or nonbuffer mode with equal proportion and equal quantity (pixel sample), as well as panoramic information sampling (image sample). The included model structures mainly focused on the models commonly used in rice mapping [i.e., Random Forest (RF) and Unet as traditional pixel and image data-driven machine-learning models], and related advanced model structures (i.e., popular transformer and Unet's variant, TransUnet, served as advanced model structures compared to the corresponding model structures commonly used in rice mapping). The experimental results showed that, when image sample was annotated well, both Unet and TransUnet were more suitable for rice mapping based on Sentinel-1 images, and their overall accuracies could reach 95% as sample size increased. Otherwise, when pixel sample size exceeded 100 000-level, nonbuffer equal proportion sampling–advanced transformer combination could be the currently optimal selection over the combination of this sampling method and RF, and its overall accuracy could reach 91% as sample size increased. Besides, it was worth noting that for data-driven machine-learning models commonly used in rice mapping, key factors for pixel data-driven ones to improve mapping accuracy was model structure upgrade, while for image data-driven ones, richness of image samples was more important.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8340-8359"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10921717","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploitation of ARIMA and Annual Variations Model for SAR Interferometry Over Permafrost Scenarios","authors":"Wenyan Yu;Xiao Cheng;Mi Jiang","doi":"10.1109/JSTARS.2025.3550748","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550748","url":null,"abstract":"The temperature change is expected to induce nonlinear characteristics in the annual fluctuation of permafrost. The interferometric synthetic aperture radar (InSAR) technique has demonstrated its efficacy in capturing such variations by monitoring surface deformation over time. However, turbulent atmospheric phase noise often requires spatiotemporal filtering, resulting in a loss of temporal resolution for nonlinear signals. Furthermore, the influence of interannual temperature variations on annual freeze–thaw cycles has not been fully integrated into InSAR modeling thus far. In this study, we propose a methodology to enhance the effectiveness of InSAR time-series analysis in permafrost environments. Diverging from conventional filtering methods where the temporal resolution loss depends on the size of the convolution kernel, we introduce the autoregressive integrated moving average model to extract the nonlinear deformation signal component. Additionally, we derive parameters associated with annual variations from the time-series deformation data during InSAR permafrost modeling. Through synthetic data experiments incorporating various noise delays, we observe a considerable improvement in accuracy, ranging from 27.8% to 55.3% in nonlinear time-series deformation analysis. Leveraging Sentinel-1 datasets from 2017 to 2021 alongside ground truth data from northern Alaska, we ascertain an enhancement of over 22% in the accuracy of time-series deformation estimation. Furthermore, incorporating annual variations enhances the accuracy of active layer thickness estimation. Our methodology reveals a strong correlation between residual deformations and soil moisture content, shedding light on the pivotal role of soil moisture in permafrost thawing processes.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8938-8952"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10923631","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RainHCNet: Hybrid High-Low Frequency and Cross-Scale Network for Precipitation Nowcasting","authors":"Lei Wang;Zheng Wang;Wenjun Hu;Cong Bai","doi":"10.1109/JSTARS.2025.3549678","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549678","url":null,"abstract":"Precipitation nowcasting, particularly predicting heavy rainfall, is a critical aspect of meteorological forecasting. Recent advancements in deep learning have led to the development of radar echo extrapolation methods. However, most convolutional neural network-based methods focus primarily on high-frequency information, neglecting essential low-frequency cues necessary for forecasting high-intensity rainfall. Although some methods introduce attention mechanisms to improve predictions, they often encounter computational challenges and suffer from information loss related to rainfall. To address these limitations, we propose RainHCNet, a streamlined novel precipitation nowcasting method built on the UNet architecture. RainHCNet incorporates a hybrid channel–spatial attention mechanism to effectively capture low-frequency information, overcoming the limitations of traditional CNN-based methods that are unable to model global dependencies. In addition, a cross-scale supervision module integrates multiscale features from both deep and shallow layers to mitigate information loss. Moreover, a dynamic adjustment strategy for loss weights is employed, focusing on low-frequency information and samples linked to high-intensity rainfall events. We present two variants of the proposed architecture: RainHCNet (6.78 M) and RainHCNet^{<inline-formula><tex-math>$dag$</tex-math></inline-formula>} (0.35 M), the latter being a lightweight version suitable for computation and memory-constrained environments. Extensive experiments on the KNMI, Shanghai, and SEVIR datasets demonstrate that both models outperform state-of-the-art methods, particularly in predicting high-intensity rainfall events.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8923-8937"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10918910","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143800927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MSPT: A Transformer-Based Model Using Multiscale Periodic Information for 10–30 d Subseasonal Daily Sea Surface Temperature Forecasting","authors":"Qi He;Zhenfeng Lan;Wei Song;Wenbo Zhang;Yanling Du;Wei Zhao","doi":"10.1109/JSTARS.2025.3549524","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549524","url":null,"abstract":"Accurately subseasonal daily sea surface temperature prediction (SSTP) is significant for forecasting and mitigating extreme climate events related to sea surface temperature (SST). However, this scale's forecasting lies at the transitional zone between short-term forecasting and long-term climate prediction, requiring simultaneous consideration of small-scale variations crucial for the former and large-scale variations fundamental to the latter. Thus, achieving precise subseasonal daily SSTPs is challenging. In this study, we introduce a novel multiscale periodic transformer (MSPT) to predict subseasonal daily SST, which can account for temporal variations at various scales. Initially, MSPT integrates fast Fourier transform and multilayer perceptron to extract all potential periodic scales and adaptively identify critical ones. Each periodic scale features an independent branch composed of patch embedding and Transformer encoder, dedicated to specifically learning temporal variations at that scale. Only the outputs of critical branches are weighted and aggregated to obtain effective multiperiodic scale characteristics. This approach effectively decouples complex temporal patterns, enabling the model to capture reliable dependencies that are beneficial for improving subseasonal forecasting. Furthermore, by introducing additional multivariate attention, our improved Transformer encoder can capture the inherent multivariate correlations of SST dynamics, perfecting the representation of temporal variations at specific periodic scales. Extensive subseasonal forecasting experiments conducted at four locations in the South China Sea demonstrate that MSPT achieves state-of-the-art performance in 10–30 d subseasonal daily SSTPs, validating the effectiveness of multiscale periodic information in improving subseasonal forecasting.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8399-8415"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10919018","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Carbonate Reservoir Hydrocarbon Detection Using Multiseismic Features Constrained Unsupervised Machine Learning","authors":"Jun Wang;Junxing Cao;Zhege Liu;Shuang Zhao","doi":"10.1109/JSTARS.2025.3549965","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549965","url":null,"abstract":"Reservoir hydrocarbon detection is of great interest for reservoir characterization and quality assessment. However, deep carbonate reservoirs exhibit weak seismic response features, making it extremely difficult to extract and utilize reservoir information from seismic data, which leads to significant challenges for seismic-based reservoir detection techniques. The sparsity of the labeled samples often limits the application of supervised machine learning for seismic reservoir detection. This study proposes a multiseismic features constrained unsupervised machine learning approach for carbonate reservoir hydrocarbon detection in areas with few or no wells, which combines the multiple reservoir fluid feature extraction methods seismic-print analysis, high-resolution seismic attenuation gradient estimation, seismic dispersion analysis, and prestack simultaneous inversion, as well as advanced unsupervised machine learning isolation forest anomaly detection algorithm, to effectively extract and utilize the implicit reservoir pore-fluid information in seismic data. This method jointly uses multiple methods to extract multiseismic data features, which can overcome the problem that using a single method to extract seismic data features cannot fully reflect the reservoir pore-fluid information. Using unsupervised machine learning for multisource data feature fusion reservoir hydrocarbon detection can solve the problem that supervised machine learning's requirement for labeled data in deep-buried reservoir detection applications cannot be met. Actual field data application shows that the hydrocarbon detection results were consistent with the actual geologic understanding, which proves that the presented method is feasible and effective. This study provides a valuable insight and reference for reservoir detection in deep carbonate reservoirs with weak seismic responses.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8910-8922"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10919050","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143800867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SBDNet: A Scale and Edge Guided Bidecoding Network for Land Parcel Extraction","authors":"Wei Wu;Yapeng Liu;Lixin Tang;Haiping Yang;Liao Yang;Jin Li;Zuohui Chen","doi":"10.1109/JSTARS.2025.3549506","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549506","url":null,"abstract":"Remote sensing-based agricultural land parcel extraction is important for managing agricultural production, monitoring farmland utilization, and supporting agricultural development planning. High-precision parcel extraction requires the simultaneous acquisition of boundary and semantic information, which is usually achieved by multitask learning. However, semantic segmentation tasks require deeper features to capture global information, while edge detection relies more on shallow features to better capture boundary details. It is difficult to learn the features of both by the same network structure. In addition, small targets are easily lost in the process, and the boundary may be broken, further affecting the accuracy of the task. To address this challenge, we propose the scale and edge guided bidecoding network (SBDNet), a novel parcel extraction framework that employs a multitask cotraining strategy. The encoder shares parameters between different tasks to improve efficiency, while the decoding phase uses U- and bidirectional flow-shaped dual decoding architectures to extract deep semantic features and shallow edge features, respectively. In addition, we incorporate a scale-attention mechanism and edge guidance modules to improve the detection of small and fragmented parcels and enhance edge coherence. Experimental results show that SBDNet outperforms existing methods, such as HRNet, DeepLabV3+, SegFormer, and semantic edge-aware networks in terms of F1 score and intersection over union (IoU). Compared with the second-ranked method, SBDNet improves the F1 score and IoU by 1.22% and 1.43%, respectively, in terms of semantic accuracy, and 1.32% and 1.88%, respectively, in terms of edge accuracy.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8057-8070"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10918777","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pine Wilt Disease Monitoring Using Multimodal Remote Sensing Data and Feature Classification","authors":"Xin Ye;Hanwen Yu;Yan Yan;Tieming Liu;Yan Zhang;Taoli Yang","doi":"10.1109/JSTARS.2025.3549977","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549977","url":null,"abstract":"Pine wilt disease (PWD) is a significant global threat to pine trees, often referred to as the “cancer of pines.” It poses a severe risk to the ecological diversity and forest resources of pine forests, making effective monitoring and control critical in global vegetation protection. With advancements in artificial intelligence (AI) and remote sensing technologies, new solutions have emerged for PWD monitoring. However, existing AI-based methods typically rely on high-resolution optical images (e.g., satellite or unmanned aerial vehicle images), which are vulnerable to environmental factors such as clouds and fog, posing challenges for practical applications. To address this, the present study introduces temporal moisture content data derived from synthetic aperture radar (SAR) and aims to combine it with optical data through a multimodal data fusion approach for more effective PWD monitoring. To facilitate practical implementation, we developed a deep learning-based model, PWD-Net, which efficiently integrates these multimodal data for the monitoring of diseased pine trees. Statistical analysis of SAR-derived moisture content reveals significant differences in moisture variation patterns between diseased and healthy trees, enhancing the interpretability of the input features for the neural network. Experimental results demonstrate that PWD-Net achieves excellent generalization across different regions, handles cross-year data effectively, and shows strong robustness to spatial and temporal variations.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8536-8546"},"PeriodicalIF":4.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10919026","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatially Resolved River Monitoring by UAV-Borne 4D-Imaging Radar: Experiments and Preliminary Validation","authors":"Giordano Cicioni;Federico Alimenti;Timo Grebner;Julian Kanz;Ron Riekenbrauck;Christian Waldschmidt","doi":"10.1109/JSTARS.2025.3549772","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549772","url":null,"abstract":"There is growing research interest in monitoring river discharge using noncontact sensors that do not require direct interaction with the water and can be mounter on unmanned aerial vehiclesto reach inaccessible areas. To this end, novel hydrodynamic models are being developed that allow the estimation of river discharge from river surface velocity measurements combined with bathymetry and water level. This research presents a novel data processing method for analyzing the surface velocity distribution of water flows using a 77-GHz 4-D imaging frequency modulated continuous wave (FMCW) radar sensor. Targets detected in the radar field-of-view are interpreted as surface velocity contributions, with the value of the surface velocity inferred from the radial component measured by the radar. We will first validate the sensor and algorithm in a controlled laboratory environment, and then deploy the system in various river environments, using both tripod-based and unmanned aerial vehicle (UAV)-based configurations. The final output, a georeferenced composite image derived from multiple UAV acquired radar images, provides detailed insights into complex, nonlaminar water flow patterns.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8071-8082"},"PeriodicalIF":4.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10919021","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}