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

筛选
英文 中文
Enhancing Ground-Based SAR Monitoring With PCA-Based Geometry Transformation for Improved Phase Unwrapping 利用基于 PCA 的几何变换改进相位解缠,加强地面合成孔径雷达监测
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-26 DOI: 10.1109/JSTARS.2025.3542115
Matthieu Rebmeister;Andreas Schenk;Stefan Hinz;Frédéric Andrian;Maxime Vonié
{"title":"Enhancing Ground-Based SAR Monitoring With PCA-Based Geometry Transformation for Improved Phase Unwrapping","authors":"Matthieu Rebmeister;Andreas Schenk;Stefan Hinz;Frédéric Andrian;Maxime Vonié","doi":"10.1109/JSTARS.2025.3542115","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3542115","url":null,"abstract":"Ground-based synthetic aperture radar (GB-SAR) systems are most often used for landslide and open-pit mine monitoring due to their high temporal sampling and spatial coverage. For infrastructure monitoring, it has not yet attained widespread adoption for this purpose, mainly due to the complex imaging geometry and related challenges for phase unwrapping. In case of vertical structures, the GB-SAR projection geometry induces strong layover and foreshortening that may be difficult to handle during phase unwrapping. In this letter, we present an approach based on principal component analysis to transform the GB-SAR interferograms into a suitable geometry, to ease the phase unwrapping, making it more efficient and more robust against unwrapping errors. The method is tested on a distorted imaging scenario at the Enguri Dam in Georgia. The results show a strong improvement of the phase unwrapping and encourage the usage of this method in the case of interferometric analysis of strongly distorted SAR images. Depending on the scenario, the subsequent required filtering may remove local deformation patterns, but considerably increases the consistency of the global displacement pattern. Two displacement maps after correction for atmospheric and repositioning influences are presented and compared with a numerical simulation based on a model calibrated with the plumblines inside the dam. The comparison shows an overall good agreement between numerical simulations and the displacement maps.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7682-7693"},"PeriodicalIF":4.7,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10906375","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667520","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}
引用次数: 0
A Selective Semantic Transformer for Spectral Super-Resolution of Multispectral Imagery 用于多光谱图像光谱超分辨率的选择性语义变换器
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-25 DOI: 10.1109/JSTARS.2025.3545039
Chengle Zhou;Zhi He;Guanglin Lai;Antonio Plaza
{"title":"A Selective Semantic Transformer for Spectral Super-Resolution of Multispectral Imagery","authors":"Chengle Zhou;Zhi He;Guanglin Lai;Antonio Plaza","doi":"10.1109/JSTARS.2025.3545039","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3545039","url":null,"abstract":"Spectral super-resolution (SSR) is an important research area. It amounts at increasing the spectral resolution of a multispectral image (MSI) with a few spectral bands to obtain a hyperspectral image (HSI) with hundreds of narrow spectral bands. State-of-the-art SSR methods typically use the transformer (or its variants) to learn the spectral mapping from the MSI to the HSI. However, these methods tend to suffer from the interference of dissimilar structures due to the constraints imposed by patch-level operations. Besides, model interpretability is attributed to prior information (from data preprocessing) rather than from an end-to-end a priori learning paradigm. To address these limitations, we propose a new selective semantic transformer (SST) for SSR. Our newly developed approach first characterizes contextual semantics within homogeneous regions and realizes information interaction from heterogeneous regions. Specifically, a superpixel-based spectral learning (SSL) strategy is designed to take into account excitated-transformer spatial and spectral semantic learning, including intra- and intersuperpixel relations, as well as superpixel edge details. Moreover, multiscale and dense residual connection mechanisms are employed to model SSL modules into an end-to-end interpretable deep network for SSR. We first conducted experiments using three well-known airborne and satellite-based datasets and then evaluated the SSR performance of our method using satellite data collected from Sentinel-2 (MSI) and GF-5 (HSI) satellites. Our results demonstrate that the newly proposed SST outperforms state-of-the-art SSR methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7436-7450"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902158","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143655088","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}
引用次数: 0
DAKBNet: Multiscale Fusion With Dynamic Assembly Kernels and Bilateral Feature Enhancement for Land Use Classification of Remote Sensing Images
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-25 DOI: 10.1109/JSTARS.2025.3545365
Chenke Yue;Yin Zhang;Junhua Yan;Zhaolong Luo;Yong Liu;Pengyu Guo
{"title":"DAKBNet: Multiscale Fusion With Dynamic Assembly Kernels and Bilateral Feature Enhancement for Land Use Classification of Remote Sensing Images","authors":"Chenke Yue;Yin Zhang;Junhua Yan;Zhaolong Luo;Yong Liu;Pengyu Guo","doi":"10.1109/JSTARS.2025.3545365","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3545365","url":null,"abstract":"Land use classification poses significant challenges when applied to remote sensing images. Due to the complex textures, spatial layouts, and scale variations of images, many methods solve these problems by ignoring the bias between low-level and high-level features caused by multiple semantic information associated with each pixel and the effectiveness of multiscale fusion. To tackle the challenges, we propose a novel bidirectional feature enhancement network based on dynamic assembled kernels, which captures both low-level spatial and high-level semantic information of the corrected image through mutual guidance between deep and shallow features. Specifically, we employ high-level semantic features derived from the bilateral structure to compute the semantic deviation of each pixel in the low-level features. Meanwhile, we use the low-level features to resolve redundant information in the high-level components and enhance their global and local context through mutual guidance. On the other hand, we generate kernels by dynamically assembling elementary weight matrices stored in the weight library. The kernel construction is data driven, providing greater flexibility to multiscale features. We have conducted extensive objective and subjective comparative experiments, as well as ablation studies, on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen, ISPRS Potsdam, and GaoFen Image Dataset. In conclusion, our method has demonstrated notable superiority over other prevailing methods, as evidenced by numerous experimental results.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7117-7133"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902592","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706598","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}
引用次数: 0
Spectral–Spatial Attention-Guided Multi-Resolution Network for Pansharpening
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-25 DOI: 10.1109/JSTARS.2025.3543827
Shen Xu;Shengwei Zhong;Hui Li;Chen Gong
{"title":"Spectral–Spatial Attention-Guided Multi-Resolution Network for Pansharpening","authors":"Shen Xu;Shengwei Zhong;Hui Li;Chen Gong","doi":"10.1109/JSTARS.2025.3543827","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543827","url":null,"abstract":"Pansharpening is a technique that combines high-resolution panchromatic (PAN) images with low-resolution multispectral (MS) images to produce high-resolution MS (HRMS) images. Deep learning-based pansharpening have outperformed traditional methods on detail injection and spectral preserving. However, existing methods often directly learn the mapping between PAN, MS, and fused HRMS, without considering the spectral–spatial feature correlation in separate bands among PAN, low-resolution PAN (LRPAN), and MS. To address this limitation, we propose a novel network called spectral–spatial attention-guided multiresolution network (SSA-MRN). Initially, SSA-MRN incorporates LRPAN images to capture the intermediate features between MS and PAN images. It also uses the individual bands of MS to learn band-specific features. Based on the comprehensive features, the spectral–spatial attention integration (SSAI) module is introduced at various scales. SSAI leverages a dot-product attention mechanism to selectively enhance the associative spectral–spatial features between PAN images and MS images across different spectral bands. The features learned by the SSAI are progressively fused at each resolution to produce the final output. Experiments on two benchmark datasets are conducted at both reduced-resolution and full-resolution. Results demonstrate that our SSA-MRN significantly enhances pansharpening quality compared to five classical methods and four state-of-the-art deep learning-based methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7559-7571"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902025","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654860","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}
引用次数: 0
Beyond Full Labels: Energy-Double-Guided Single-Point Prompt for Infrared Small Target Label Generation
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-25 DOI: 10.1109/JSTARS.2025.3545014
Shuai Yuan;Hanlin Qin;Renke Kou;Xiang Yan;Zechuan Li;Chenxu Peng;Dongliang Wu;Huixin Zhou
{"title":"Beyond Full Labels: Energy-Double-Guided Single-Point Prompt for Infrared Small Target Label Generation","authors":"Shuai Yuan;Hanlin Qin;Renke Kou;Xiang Yan;Zechuan Li;Chenxu Peng;Dongliang Wu;Huixin Zhou","doi":"10.1109/JSTARS.2025.3545014","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3545014","url":null,"abstract":"In this article, we pioneer a learning-based single-point prompt paradigm for infrared small target label generation (IRSTLG) to lobber annotation burdens. Unlike previous clustering-based methods, our intuition is that point-guided mask generation just requires one more prompt than target detection, i.e., IRSTLG can be treated as an infrared small target detection (IRSTD) with the location hint. Therefore, we propose a simple yet effective energy-double-guided single-point prompt (EDGSP) framework, aiming to adeptly transform a coarse IRSTD network into a refined label generation method. Specifically, EDGSP comprises three key modules: first, target energy initialization, which establishes a foundational outline to streamline the mapping process for effective shape evolution, second, double prompt embedding for rapidly localizing interesting regions and reinforcing high-resolution individual edges to avoid label adhesion, and third, bounding box-based matching for eliminating false masks via considering comprehensive cluster boundary conditions to obtain a reliable output. In this way, pseudolabels generated by three backbones equipped with our EDGSP achieve 100% object-level probability of detection (<inline-formula><tex-math>${{P}_{d}}$</tex-math></inline-formula>) and 0% false-alarm rate (<inline-formula><tex-math>${{F}_{a}}$</tex-math></inline-formula>) on SIRST, NUDT-SIRST, and IRSTD-1k datasets, with a pixel-level intersection over union improvement of 13.28% over state-of-the-art label generation methods. Further applying our inferred masks to train detection models, EDGSP, for the first time, enables a single-point-generated pseudomask to surpass the manual labels. Even with coarse single-point annotations, it still achieves 99.5% performance of full labeling.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8125-8137"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902427","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706588","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}
引用次数: 0
Progressive Enhancement of Foreground Features for Salient Object Detection in Optical Remote Sensing Images
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-25 DOI: 10.1109/JSTARS.2025.3545681
Lingbing Meng;Haiqun Li;Huihui Han;Meng Xu;Jinhua Wu;Shuonan Hou;Weiwei Duan
{"title":"Progressive Enhancement of Foreground Features for Salient Object Detection in Optical Remote Sensing Images","authors":"Lingbing Meng;Haiqun Li;Huihui Han;Meng Xu;Jinhua Wu;Shuonan Hou;Weiwei Duan","doi":"10.1109/JSTARS.2025.3545681","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3545681","url":null,"abstract":"Salient object detection (SOD) in optical remote sensing images (ORSI) has attracted considerable attention in recent years. With the rapid advancement of deep learning techniques, ORSI-SOD development has been remarkable. However, existing models continue to encounter significant challenges in processing certain scenarios, such as those consisting of low contrast, complex boundaries, and cluttered backgrounds. To address these challenges, we propose a progressive enhancement of the foreground feature network (PEFFNet) for ORSI-SOD, which is a novel three-stage design. In the first stage, a semantic-guided feature fusion module is introduced that adopts a top–down approach to effectively integrate multilevel feature information. This fusion strategy preserves the rich semantic information of the remote sensing object and accurately captures boundary detail features such that highly accurate initial optical remote sensing saliency map (ORSSM) can be generated. In the second stage, a simple and efficient feature enhancement module is designed, which consists of a background suppression module (BSM) and a bottom–up feature interaction module (BUFIM). The BSM utilizes an initial ORSSM to suppress background features, which significantly reduces interference from nonremote sensing regions. BUFIM enhances the feature representation of objects at different levels and optimizes object boundaries by fusing adjacent levels of features. In the third stage, a reverse attention decoding module is proposed to address pixel inhomogeneity and blurring in the remote sensing region. Experimental results demonstrate superior PEFFNet performance over other state-of-the-art models on three datasets on the basis of both quantitative and qualitative evaluations.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7572-7591"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902559","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143655090","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}
引用次数: 0
DAFDM: A Discerning Deep Learning Model for Active Fire Detection Based on Landsat-8 Imagery
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-25 DOI: 10.1109/JSTARS.2025.3545114
Xu Gao;Wenzhong Shi;Min Zhang;Lukang Wang
{"title":"DAFDM: A Discerning Deep Learning Model for Active Fire Detection Based on Landsat-8 Imagery","authors":"Xu Gao;Wenzhong Shi;Min Zhang;Lukang Wang","doi":"10.1109/JSTARS.2025.3545114","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3545114","url":null,"abstract":"Monitoring active fire (AF) utilizing remote sensing imagery provides critical support for fire rescue and environmental protection. Traditional methods for detecting AFs rely on the statistical analysis of AF radiance and background features. However, these algorithms are resource-intensive to develop and exhibit limited adaptability, particularly in distinguishing AF from interference pixels. Deep learning (DL) technologies, which can extract deep features from images, offer a new solution for efficiently detecting AF. This article proposes an AF detection model based on convolutional neural networks, named DAFDM. By integrating multilayer features through an enhanced feature processing module, the model produces high-quality AF information, accurately detecting AF from the background. Given the presence of uncorrected false alarms in the training labels, it is challenging for DL models to distinguish interference pixels, we construct a Landsat-8 dataset encompassing various fire types and interference objects, with precise labels. Comparing several architectures, we find that only U-Net type models can discern the AF boundary pixels fully and accurately. The proposed method outperforms other AF detection algorithms, achieving IoU and F1-score of 87.28% and 93.21%, respectively. Experimental results demonstrate that DAFDM possesses robust generalization capability in distinguishing interference pixels. The incorporation of land surface temperature as auxiliary data further improves DAFDM's performance, with interpretability methods employed to elucidate the impact of input data on predictions. This method is anticipated to further contribute to AF monitoring and wildfire development pattern analysis.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7982-8000"},"PeriodicalIF":4.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902470","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706713","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}
引用次数: 0
Low-Latency Neural Network for Efficient Hyperspectral Image Classification
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-24 DOI: 10.1109/JSTARS.2025.3544583
Chunchao Li;Jun Li;Mingrui Peng;Behnood Rasti;Puhong Duan;Xuebin Tang;Xiaoguang Ma
{"title":"Low-Latency Neural Network for Efficient Hyperspectral Image Classification","authors":"Chunchao Li;Jun Li;Mingrui Peng;Behnood Rasti;Puhong Duan;Xuebin Tang;Xiaoguang Ma","doi":"10.1109/JSTARS.2025.3544583","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544583","url":null,"abstract":"Hyperspectral image classification (HSIC) has been considerably improved by many lightweight and efficient networks developed to meet real-time application needs and computing resource limitations. However, theoretical floating-point operations alone are not enough to evaluate real-time quality, especially in scenarios where inference latency is highly influenced by memory access cost and hardware characteristics. To address these challenges, we create a low-latency-oriented network architecture for HSIC, which is adaptable to any dataset without requiring architectural adjustments. First, starting from a pretrained backbone network, we deploy a latency-oriented network architecture search, with search flexibility spanning multiple levels of the model, and add inference latency as a model evaluator to identify low-latency subnetwork architectures adapted to hyperspectral data. Moreover, we develop a computational efficiency model that can anticipate and evaluate the peak performance of operators that use hyperspectral input. Based on this, we introduce a split convolution approach that replaces depthwise convolution, resulting in enhanced arithmetic intensity without significant increase in latency. The networks created by implementing our strategies are both compact in structure and hardware-friendly. After testing on three different datasets, the proposed networks achieve significantly better inference speed and energy-saving ability over advanced classification networks and lightweight models, while maintaining an equivalent or even better classification performance.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7374-7390"},"PeriodicalIF":4.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10900438","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645342","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}
引用次数: 0
Evaluating the Environmental Impact: A Multisensor Remote Sensing Approach for Spatial and Temporal Analysis
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-24 DOI: 10.1109/JSTARS.2025.3544642
Bin Zhu;Ahsen Maqsoom;Lapyote Prasittisopin;Chaudhary Danyal Aslam;Umer Khalil;Sahar Zia;Niamat Ullah;M. Abdullah-Al-Wadud;Nazih Yacer Rebouh
{"title":"Evaluating the Environmental Impact: A Multisensor Remote Sensing Approach for Spatial and Temporal Analysis","authors":"Bin Zhu;Ahsen Maqsoom;Lapyote Prasittisopin;Chaudhary Danyal Aslam;Umer Khalil;Sahar Zia;Niamat Ullah;M. Abdullah-Al-Wadud;Nazih Yacer Rebouh","doi":"10.1109/JSTARS.2025.3544642","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544642","url":null,"abstract":"This study quantifies the potential environmental impacts of the Karakoram highway (KKH) construction, which links the northern region of Pakistan with Western China. The upgrade of the KKH was carried out under the China-Pakistan Economic Corridor (CPEC) project. We examined highway construction's spatial and temporal effects on the immediate environment and the ecological revival progressions through remotely sensed images taken at distinct points in time. Here, using a buffer zone of 20 km along the KKH (10 km on both sides), we estimated the before-during-after remote sensing-based factors that relate to the ecology to compute the geographical and temporal variations of environmental effects during the building of the KKH. The outcomes showed that whereas land cover makeup remained broadly consistent in the south of the buffer, it underwent significant changes in the upper portion as we moved more and more towards the north. The buffer region showed clear degradation-recovery trends in the moistness and vegetation states, as evidenced by the normalized difference moisture index (NDMI) and the normalized difference vegetation index (NDVI) correspondingly. Meanwhile, the land surface temperature (LST) gradually increased. The maximum relative changes in NDMI, NDVI, and LST were roughly 60%, 40%, and 12%, respectively. According to an Integrated environment quality index, the effects of highway developments on the environment were most pronounced in the immediate vicinity and diminished with distance. This study's method for quantifying highway system disturbances' spatial and temporal changes and subsequent recovery can be easily extended to different geographical areas.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7189-7206"},"PeriodicalIF":4.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10900415","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621673","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}
引用次数: 0
Multimodal Fusion Learning for Predicting Tropical Cyclone Intensity Over Western North Pacific
IF 4.7 2区 地球科学
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-24 DOI: 10.1109/JSTARS.2025.3544865
Jie Lian;Jiahao Shao;Hui Yu;Ruirong Chen;Sirong Huang;Guomin Chen;Qin Zhao
{"title":"Multimodal Fusion Learning for Predicting Tropical Cyclone Intensity Over Western North Pacific","authors":"Jie Lian;Jiahao Shao;Hui Yu;Ruirong Chen;Sirong Huang;Guomin Chen;Qin Zhao","doi":"10.1109/JSTARS.2025.3544865","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544865","url":null,"abstract":"Tropical cyclones (TCs) are highly destructive weather phenomena that cause extensive human and economic losses in affected regions. Accurate prediction of tropical cyclone intensity (TCI) is crucial for disaster preparedness and mitigation. Traditional TCI forecasting methods fail to extract nonlinear features and suffer from high computation costs. In recent years, deep learning methods have been increasingly used to address this challenge. However, current approaches often underutilize meteorological variables and satellite cloud imagery, and fail to capture correlations between multimodal data. In this article, we propose TCIque, a sequence-to-sequence model specifically designed for TCI forecasting. TCIque is designed to integrate multimodal data and retrieve correlational features between them based on the Wide and Deep concept. The “Wide” component leverages domain knowledge to extract statistical features, while the “Deep” component captures nonlinear correlations and spatio-temporal dynamics based on self-attention mechanisms. This unique combination allows the model to fully utilize diverse data sources, such as meteorological variables, satellite imagery, and expert-driven features, ensuring robust feature fusion. Furthermore, a predictive encoder–decoder architecture associated with the self-attention mechanism is employed to address the challenge of long-term dependency decay. Experimental results demonstrate that the TCIque model outperforms existing methods, achieving more accurate performance in TCI prediction by 60.9%, 51.6%, 39.2%, and 1.8% compared to the best performance of baselines, which includes ConvLSTM, PredRNN, TC-Pred, SCSTque, SAF-Net, TCI-Net, Tint, and Pred_3d at 6h, 12h, 18h, and 24h forecast, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7048-7063"},"PeriodicalIF":4.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10900423","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621721","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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信