{"title":"3-D UXSE-Net for Seismic Channel Detection Based on Satellite Image Enhanced Synthetic Datasets","authors":"Xinke Zhang;Yihuai Lou;Naihao Liu;Daosheng Ling;Yunmin Chen","doi":"10.1109/JSTARS.2025.3550578","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550578","url":null,"abstract":"Channels are essential indicators of sedimentary environments and play a vital role in geological applications, such as hydrocarbon exploration, sediment transport, and the study of ancient river geomorphology. Deep learning (DL) techniques have shown great potential in improving channel detection accuracy and efficiency. However, insufficient labeled training data remains a key challenge for refining DL models. To address this issue, we propose a workflow that automatically generates synthetic datasets by integrating channel features extracted from high-resolution satellite images. We first extract river channel features and grayscale values from satellite images. These extracted features are then used to construct reflectivity models, incorporating structural deformations based on seismic reflector dips. The reflectivity models are subsequently convolved with wavelets to generate synthetic datasets. These synthetic datasets are used to train the proposed 3-D UXSE-Net, which integrates the 3-D UX-Net architecture with the squeeze-and-excitation blocks. The model generates improved feature representations that enhance performance by combining convolutional neural networks for local feature extraction and Transformer-based modules for capturing global context. We validate our approach by applying the model to both synthetic and 3-D field seismic datasets. Our results show that 3-D UXSE-Net outperforms baseline methods, including the coherence-based approach and other DL models, and demonstrates strong generalization to field data even when trained solely on synthetic data. Comparisons of different methods highlight the effectiveness of the synthetic data generation approach for DL model training.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8300-8311"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10923698","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740374","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":"MSFCN: A Multiscale Feature Correlation Network for Remote Sensing Image Scene Change Detection","authors":"Feng Xie;Zhongping Liao;Jianbo Tan;Zhiguo Hao;Shining Lv;Zegang Lu;Yunfei Zhang","doi":"10.1109/JSTARS.2025.3549471","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549471","url":null,"abstract":"Scene-level change detection identifies land use changes and determines change types from a high-level semantic perspective, which is significant for monitoring urbanization. The existing advanced methods are generally based on Siamese networks that utilize the feature correlation of bitemporal scenes or introduce change information to enhance the feature representation. However, their extraction of feature correlation is insufficient to improve the model performance further. This article proposed a Siamese-based multiscale feature correlation network (MSFCN) to enhance the correlation extraction process. First, 1-D multiscale local features are obtained by the designed space-channel self-calibration module and multiscale local feature extraction module. Then, these features are inputted into the proposed multiscale feature correlation module to extract feature correlation. Finally, the dual-branch features are fused based on the feature correlation to generate more discriminative 1-D deep features. In addition, cosine embedding loss is used to constrain the scene binary change detection task and construct a multitask loss for model optimization. On the Hanyang and WH-MAVS datasets, MSFCN achieved average scene classification accuracies of 93.33% and 94.86%, scene-level binary change detection accuracies of 95.71% and 98.13%, and scene-level semantic change detection accuracies of 90.00% and 93.95%, respectively, significantly better than the comparison methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8275-8299"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10923708","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740338","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":"A Low Signal-to-Noise Ratio Infrared Small-Target Detection Network","authors":"Fenghong Li;Peng Rao;Wen Sun;Yueqi Su;Xin Chen","doi":"10.1109/JSTARS.2025.3550581","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550581","url":null,"abstract":"Space-based infrared detection technology is critical to space situational awareness, playing a significant role in noncooperative space object detection, threat perception, and space target surveillance. As space-based infrared detection technology evolves, the primary challenge is detecting more distant objects and achieving high precision in the detection of space targets with lower signal-to-noise ratios (SNRs). Owing to the scarcity of space-based data, existing methods for infrared small target detection (IRSTD) focus on high-SNR terrestrial images and perform poorly with extremely low-SNR space targets. We propose a novel low SNR space-based IRSTD network. We present a trajectory encoding enhancement module that uses multiframe data to accumulate energy along the target's trajectory. It leverages multiframe temporal information, effectively enhancing the target while suppressing the background. This module can be integrated into most single-frame target detection networks. Additionally, we combine residual networks with global context aggregation to enhance the network's ability to extract features from small infrared targets. In the feature fusion phase, we propose a multiscale perception fusion module that expands the receptive field of shallow features and integrates multiscale information to accurately detect targets. We conduct extensive validation on real infrared space target datasets and semisimulated datasets, and our approach achieves the best performance. For targets with an SNR of 0.7, over 97% detection and fewer than 10<sup>–6</sup> false alarms are achieved.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8643-8658"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10924406","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777881","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}
Manuela F. Cerón-Viveros;Wolfgang Maass;Jiaojiao Tian
{"title":"OA-WinSeg: Occlusion-Aware Window Segmentation With Conditional Adversarial Training Guided by Structural Prior Information","authors":"Manuela F. Cerón-Viveros;Wolfgang Maass;Jiaojiao Tian","doi":"10.1109/JSTARS.2025.3550632","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550632","url":null,"abstract":"Window segmentation and vectorization remains a significant challenge, particularly in the absence of clean facade images. To extract complete window segments from building façade images with occlusions, this article proposes an occlusion-aware window segmentation <italic>(OA-WinSeg)</i> network with conditional adversarial training guided by prior structural information. This architecture combines the power of image segmentation and generative capabilities to handle occlusions. First, <italic>OA-WinSeg</i> automatically detects occlusions and generates a rectangular boundary guidance from a coarse window segmentation, which incorporates structural information about the building layout into the process. Subsequently, the network refines the coarse segmentation and generates window segments in the missing regions by attending to contextual information of the nonoccluded parts of the façade. Finally, our approach generates accurate vector representations, information needed for building modeling systems. Experimental results demonstrate the effectiveness of our model with simulated and occluded real-world datasets. In addition, we evaluate our model on various ablation studies to explore the contribution of the different modules. Finally, we have analyzed the potential applications of the proposed segmentation network and the completed window segments, including building façade inpainting.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8490-8503"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10923720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761383","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":"Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production","authors":"Ruiyang Yu;Yunjun Yao;Qingxin Tang;Xueyi Zhang;Changliang Shao;Joshua B. Fisher;Jiquan Chen;Xiaotong Zhang;Yufu Li;Jia Xu;Lu Liu;Zijing Xie;Jing Ning;Jiahui Fan;Luna Zhang","doi":"10.1109/JSTARS.2025.3549373","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549373","url":null,"abstract":"It is significant to simulate grassland gross primary production (GPP) to understand the terrestrial carbon budget over Inner Mongolia (IMG), China. Nevertheless, there is not sufficient <italic>in situ</i> GPP data over this region. In this study, we proposed a novel model-based transfer learning (MTL) approach with generative adversarial networks-long short-term memory (GAN-LSTM) and light use efficiency (LUE) models to derive grassland GPP over IMG, China. We first used 25 grassland eddy covariance sites over the conterminous United States to establish the GAN-LSTM model and then fine-tuned it with six sites over IMG to estimate water constraints that were embedded into the LUE model to predict GPP. We then compared it with instance-based transfer learning and nontransfer learning approaches. Against the six IMG EC sites, the GPP estimates of MTL-LUE outperformed the other approaches with a lower root-mean-square error median (1.35 g C m<sup>−2</sup> d<sup>−1</sup>) and a higher Kling-Gupta efficiency of 0.54. An innovation of this approach is that MTL-LUE mitigates the effect of limited training samples on the machine learning-based LUE hybrid model for GPP estimates over IMG.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"9738-9754"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10923714","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835369","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":"A Novel Shape Guided Transformer Network for Instance Segmentation in Remote Sensing Images","authors":"Dawen Yu;Shunping Ji","doi":"10.1109/JSTARS.2025.3550460","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550460","url":null,"abstract":"Instance segmentation performance in remote sensing images (RSIs) is significantly affected by two issues: how to extract accurate boundaries of objects from remote imaging through the dynamic atmosphere, and how to integrate the mutual information of related object instances scattered over a vast spatial region. In this study, we propose a novel shape guided transformer network (SGTN) to accurately extract objects at the instance level. Inspired by the global contextual modeling capacity of the self-attention mechanism, we propose an effective transformer encoder termed LSwin, which incorporates vertical and horizontal 1-D global self-attention mechanisms to obtain better global-perception capacity for RSIs than the popular local-shifted-window based swin transformer. To achieve accurate instance mask segmentation, we introduce a shape guidance module (SGM) to emphasize the object boundary and shape information. The combination of SGM, which emphasizes the local detail information, and LSwin, which focuses on the global context relationships, achieve excellent RSI instance segmentation. Their effectiveness was validated through comprehensive ablation experiments. Especially, LSwin is proven better than the popular ResNet and swin transformer encoders at the same level of efficiency. Compared to other instance segmentation methods, our SGTN achieves the highest average precision scores on two single-class public datasets (WHU dataset and BITCC dataset) and a multiclass public dataset (NWPU VHR-10 dataset).","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8325-8339"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10923715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726402","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}
Bo Zhang;Li Zhang;Min Yan;Jian Zuo;Yuqi Dong;Bowei Chen
{"title":"High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data","authors":"Bo Zhang;Li Zhang;Min Yan;Jian Zuo;Yuqi Dong;Bowei Chen","doi":"10.1109/JSTARS.2025.3550878","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550878","url":null,"abstract":"Forests are vital carbon sinks, with tree height and biomass critical for carbon research. NASA's GEDI spaceborne LiDAR enhances vegetation monitoring through 3D structure analysis. This study established relationships between GEDI products and Sentinel-1/2, Landsat 8, ALOS, and GLO-30 features using the AutoML method. We constructed a total of 432 features, primarily from 14 types of earth observation features. In a 95.56% forest-covered area, AutoML improved canopy height (FCH) and biomass (AGBD) accuracy by up to 5.25 m and 32.18 Mg/ha over other methods. Polarization interference features, especially phase, explain 20% of forest parameters, showing high stability. Wavelet and Fourier-based texture features also demonstrate strong potential. Two mapping methods are proposed: 10 m resolution (FCH <inline-formula><tex-math>$R^{2}$</tex-math></inline-formula> = 0.53, RMSE = 11.49 m; AGBD <inline-formula><tex-math>$R^{2}$</tex-math></inline-formula> = 0.53, RMSE = 133.56 Mg/ha) and 500 m resolution (FCH <inline-formula><tex-math>$R^{2}$</tex-math></inline-formula> = 0.64, RMSE = 10.06 m; AGBD <inline-formula><tex-math>$R^{2}$</tex-math></inline-formula> = 0.66, RMSE = 114.25 Mg/ha). Compared to existing maps (AGBD: <inline-formula><tex-math>$R$</tex-math></inline-formula> <inline-formula><tex-math>$<$</tex-math></inline-formula> 0.1, RMSE <inline-formula><tex-math>$>$</tex-math></inline-formula> 180 Mg/ha; FCH: <inline-formula><tex-math>$R <$</tex-math></inline-formula> 0.2, RMSE <inline-formula><tex-math>$>$</tex-math></inline-formula> 15 m), our method (AGBD <inline-formula><tex-math>$R$</tex-math></inline-formula> = 0.74, RMSE = 131.39 Mg/ha; FCH <inline-formula><tex-math>$R$</tex-math></inline-formula> = 0.73, RMSE = 11.30 m) significantly improves accuracy. The approach shows minimal saturation effects and broad applicability for forest parameter estimation.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"9084-9118"},"PeriodicalIF":4.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10924716","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839955","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":"Visibility Analysis of 3D Urban Space Navigation Satellites Based on Virtual Panoramic Obstruction Images","authors":"Ruixiong Kou;Shuwen Yang;Zhuang Shi","doi":"10.1109/JSTARS.2025.3550341","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550341","url":null,"abstract":"The visibility of satellites is an important parameter for evaluating and predicting the accuracy and credibility of global navigation satellite system positioning. Since the satellite signal is easily blocked, reflected, and scattered by buildings, overpasses, and trees, the visible satellite number dramatically changes in time and space. The three-dimensional (3D) urban model, point clouds, and panoramic images are used to calculate the visibility of satellites. However, the refined urban model requires abundant manual work and is expensive, while point clouds with the characteristic of large data volume have the problem of computing efficiency low. Also, the public panoramic images only cover road areas, which can not calculate the visibility of satellites in 3D urban space. The existing methods are impossible to achieve refined, lightweight, and fast computation of the visible satellite number. Therefore, we propose the satellite visibility calculation method based on constructing virtual panoramic obstruction images through digital surface model (DSM). The required DSM range of sampling points is selected using an adaptive method considering the GNSS satellite elevation mask angle to reduce data volume. Then, the virtual panoramic obstruction imagery is constructed based on the determined range DSM, which saves time for the real-time calculation of satellite visibility. Hence, the calculation efficiency is greatly improved. To verify the effectiveness and reliability of the proposed method, we collected the experiment field point clouds and constructed high-precision DSM for calculating satellite visibility of arbitrary locations. The experiments demonstrated that the proposed method provides an easy-to-use and high-precision solution to map the spatio-temporal visibility of satellites.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8312-8324"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10921713","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726405","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":"Coastal Wetlands Classification and Carbon Storage Estimation: A Case Study of the Region Surrounding the South China Sea","authors":"Guanglin Lai;Zhi He;Chengle Zhou;Youwei Wang","doi":"10.1109/JSTARS.2025.3549480","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3549480","url":null,"abstract":"Coastal wetlands are typical carbon sinks and play a crucial role in achieving global carbon neutrality goals. The region surrounding the South China Sea (SCS) contains abundant coastal wetland resources and strong carbon sequestration capabilities, which can be effectively assessed by the well-known integrated valuation of ecosystem services and tradeoffs (InVEST) model. InVEST requires accurate spatial distribution information of wetlands as input data, which can be obtained by coastal wetlands classification methods. Among all classification methods, deep learning (DL) is the state-of-the-art. However, designing a DL method that is both easily trainable and suitable for large-scale coastal wetland classification remains a challenging issue. This article proposes a novel DL method and a new carbon correction strategy for large-scale coastal wetland classification and carbon storage assessment. First, the remote sensing (RS) data from the study area is acquired and preprocessed by the Google Earth Engine. Second, the Otsu algorithm and decision tree are used to extract the maximum wetland extent. Third, a multidirectional squeeze attention network (MDSAN) is proposed for large-scale coastal wetland classification. Finally, a new strategy is designed to correct measured carbon pool data using meteorological data. Experiments show that the proposed wetland classification method achieves an overall accuracy and Kappa coefficient of 0.9500 and 0.9411, respectively, demonstrating the effectiveness of MDSAN. Furthermore, the estimated carbon storage in the mangroves, tidal-flats, and swamps surrounding the SCS is approximately 1.2112<inline-formula><tex-math>$boldsymbol{times }10boldsymbol{^{9}}$</tex-math></inline-formula> t, 6.9138<inline-formula><tex-math>$boldsymbol{times }10boldsymbol{^{7}}$</tex-math></inline-formula> t, and 1.6980<inline-formula><tex-math>$boldsymbol{times }10boldsymbol{^{8}}$</tex-math></inline-formula> t, respectively, revealing the carbon distribution pattern in the region.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"9464-9482"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10918765","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835434","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":"A Global Extended MODIS-Compatible NDVI Dataset","authors":"Tingting Zhang;Hongyan Zhang;Yeqiao Wang;Tao Xiong;Meiyu Wang;Zhengxiang Zhang;Xiaoyi Guo;Jianjun Zhao","doi":"10.1109/JSTARS.2025.3550416","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3550416","url":null,"abstract":"The study of climate change impacts on vegetation requires access to long-time series vegetation dynamics. MODIS NDVI, with its high chlorophyll sensitivity and data quality, is an important data source in global change monitoring and ecological studies. However, as MODIS NDVI became available only after 2000, the data before 2000 are lacking. This article provides a global MODIS-compatible NDVI dataset at moderate spatial (0.05°) and temporal (16-day) resolution from 1982 to 2000. This dataset generates a long-time series of global NDVI products based on MODIS and AVHRR data using multiple optimization machine learning algorithms. It is designed to synchronously capture complex spatial and temporal correlations of multisource data and account for heterogeneity. Compared with MODIS NDVI, R<sup>2</sup> of this dataset ranged from 0.79 to 0.95, and the mean absolute error was less than 0.06 in most areas. This dataset addresses the problem of the short period of MODIS NDVI data and provides a new data choice for monitoring global vegetation dynamics and ecological studies.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8390-8398"},"PeriodicalIF":4.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10921702","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726575","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}