Transformer-based architectures have shown strong potential in hyperspectral unmixing due to their powerful modeling capabilities. However, most existing transformer-based methods still struggle to effectively capture and fuse spatial–spectral features, and their predominant reliance on reconstruction error further constrains overall unmixing performance. Moreover, they rarely account for the nonlinear correlations that inherently exist between the spatial and spectral domains. To address these challenges, we propose a sampling-based spatial–spectral transformer and generative adversarial network (SSST-GAN). The proposed model employs a dual-branch, sampling-based transformer encoder to independently extract spatial and spectral representations. Specifically, the spatial branch adopts a full-sampling multihead attention mechanism to capture rich contextual dependences among spatial pixels, while the spectral branch utilizes a sparse sampling strategy to efficiently distill key information from high-dimensional spectral data. A feature enhancement module is introduced to integrate and strengthen the complementary characteristics of spatial and spectral features. To further improve the modeling of complex nonlinear mixing patterns, we incorporate a generalized nonlinear fluctuation model at the decoding stage. In addition, SSST-GAN leverages a generative adversarial learning framework, in which a discriminator evaluates the authenticity of reconstructed pixels, thereby enhancing the fidelity of the unmixing results. Extensive experiments on both synthetic and real-world datasets demonstrate that SSST-GAN consistently outperforms several state-of-the-art methods in terms of unmixing accuracy.
{"title":"SSST-GAN: A Sampling-Based Spatial-Spectral Transformer and Generative Adversarial Network for Hyperspectral Unmixing","authors":"Yu Zhang;Jiageng Huang;Yefei Huang;Wei Gao;Jie Chen","doi":"10.1109/JSTARS.2026.3655512","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655512","url":null,"abstract":"Transformer-based architectures have shown strong potential in hyperspectral unmixing due to their powerful modeling capabilities. However, most existing transformer-based methods still struggle to effectively capture and fuse spatial–spectral features, and their predominant reliance on reconstruction error further constrains overall unmixing performance. Moreover, they rarely account for the nonlinear correlations that inherently exist between the spatial and spectral domains. To address these challenges, we propose a sampling-based spatial–spectral transformer and generative adversarial network (SSST-GAN). The proposed model employs a dual-branch, sampling-based transformer encoder to independently extract spatial and spectral representations. Specifically, the spatial branch adopts a full-sampling multihead attention mechanism to capture rich contextual dependences among spatial pixels, while the spectral branch utilizes a sparse sampling strategy to efficiently distill key information from high-dimensional spectral data. A feature enhancement module is introduced to integrate and strengthen the complementary characteristics of spatial and spectral features. To further improve the modeling of complex nonlinear mixing patterns, we incorporate a generalized nonlinear fluctuation model at the decoding stage. In addition, SSST-GAN leverages a generative adversarial learning framework, in which a discriminator evaluates the authenticity of reconstructed pixels, thereby enhancing the fidelity of the unmixing results. Extensive experiments on both synthetic and real-world datasets demonstrate that SSST-GAN consistently outperforms several state-of-the-art methods in terms of unmixing accuracy.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5741-5757"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358397","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175673","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655786
Yuxin Deng;Chuanli Kang;Zitao Lin;Xuanhao Li;Shuyue Liu;Xixi Wang
Point cloud registration is a core technology in fields such as 3D reconstruction and robot navigation. Current methods, however, struggle to balance accuracy with efficiency: the traditional Iterative Closest Point (ICP) algorithm is prone to local minima, while the Coherent Point Drift (CPD) algorithm suffers from high computational complexity. This article presents a Cascade Registration method based on Transformation Transfer for multiscale point clouds (CR-TT). Its key innovation lies in constructing a tightly coupled cascade framework where the transformation solved by coarse registration (guided by keypoints for rapid optimization) is converted into a strong prior for fine registration (driven by probability density modeling). This approach reduces the complex global optimization problem to efficient local refinement, achieving a paradigm shift from merely “improving the initial guess” to “simplifying the optimization problem itself.” Experiments on multiscale datasets demonstrate that CR-TT achieves significant advantages across small-, medium-, and large-scale scenes, with its Root Mean Square Error improved by 4.4–25.4 times over traditional ICP and CPD. Compared to state-of-the-art deep learning methods (e.g., DCP, GeoTransformer), CR-TT exhibits superior generalization capability and stability in out-of-distribution, large-scale complex scenes. In the engineering registration of point clouds for arch rib segments of a large concrete-filled steel tubular bridge, the coefficient of determination (R2) reaches 99.64%. The proposed method provides a reliable solution for efficient and robust alignment of cross-scale point clouds.
{"title":"A Cascade Registration Method Based on Transformation Transfer for Multiscale Point Clouds","authors":"Yuxin Deng;Chuanli Kang;Zitao Lin;Xuanhao Li;Shuyue Liu;Xixi Wang","doi":"10.1109/JSTARS.2026.3655786","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655786","url":null,"abstract":"Point cloud registration is a core technology in fields such as 3D reconstruction and robot navigation. Current methods, however, struggle to balance accuracy with efficiency: the traditional Iterative Closest Point (ICP) algorithm is prone to local minima, while the Coherent Point Drift (CPD) algorithm suffers from high computational complexity. This article presents a Cascade Registration method based on Transformation Transfer for multiscale point clouds (CR-TT). Its key innovation lies in constructing a tightly coupled cascade framework where the transformation solved by coarse registration (guided by keypoints for rapid optimization) is converted into a strong prior for fine registration (driven by probability density modeling). This approach reduces the complex global optimization problem to efficient local refinement, achieving a paradigm shift from merely “improving the initial guess” to “simplifying the optimization problem itself.” Experiments on multiscale datasets demonstrate that CR-TT achieves significant advantages across small-, medium-, and large-scale scenes, with its Root Mean Square Error improved by 4.4–25.4 times over traditional ICP and CPD. Compared to state-of-the-art deep learning methods (e.g., DCP, GeoTransformer), CR-TT exhibits superior generalization capability and stability in out-of-distribution, large-scale complex scenes. In the engineering registration of point clouds for arch rib segments of a large concrete-filled steel tubular bridge, the coefficient of determination (R<sup>2</sup>) reaches 99.64%. The proposed method provides a reliable solution for efficient and robust alignment of cross-scale point clouds.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"7132-7151"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11359007","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299548","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655557
Qiubai Zhu;Qinan Jia;Wenbin Xie;Chenxi Liu;Tao Shen;Zhen Zhang;Wangqing Wang
Currently, a significant portion of knowledge in the field of remote sensing (RS) is stored in unstructured formats, leading to inefficient data analysis and the formation of information silos due to fragmented data accumulation. Consequently, there is an urgent need for an effective knowledge representation and modeling framework tailored to the characteristics of RS data. Knowledge graph (KG), owing to their highly structured nature and strong interoperability, offers a promising solution by enabling rapid integration of multisource data and revealing complex interrelationships among heterogeneous datasets. This study proposes a novel approach that integrates temporal sequences with spatial information to construct a spatio-temporally evolving remote sensing KG (RSKG), thereby advancing the intelligent analysis capabilities of RS imagery. Specifically, we innovatively incorporate multitemporal, high-resolution RS image data into a unified KG framework endowed with spatio-temporal evolution properties. By representing image features within a KG structure, this approach not only improves the efficiency of spatio-temporal data management, but also enhances the applicability of large language model (LLM) in the domain-specific context of RS. Experimental results demonstrate that integrating RS imagery, geographic information, and domain expertise into a structured and evolvable knowledge system significantly strengthens the semantic expressiveness of RS data. Furthermore, it enables LLMs to better interpret spatial semantics, accurately analyze surface change dynamics.
{"title":"Construction of Remote Sensing Knowledge Graph for Spatiotemporal Analysis","authors":"Qiubai Zhu;Qinan Jia;Wenbin Xie;Chenxi Liu;Tao Shen;Zhen Zhang;Wangqing Wang","doi":"10.1109/JSTARS.2026.3655557","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655557","url":null,"abstract":"Currently, a significant portion of knowledge in the field of remote sensing (RS) is stored in unstructured formats, leading to inefficient data analysis and the formation of information silos due to fragmented data accumulation. Consequently, there is an urgent need for an effective knowledge representation and modeling framework tailored to the characteristics of RS data. Knowledge graph (KG), owing to their highly structured nature and strong interoperability, offers a promising solution by enabling rapid integration of multisource data and revealing complex interrelationships among heterogeneous datasets. This study proposes a novel approach that integrates temporal sequences with spatial information to construct a spatio-temporally evolving remote sensing KG (RSKG), thereby advancing the intelligent analysis capabilities of RS imagery. Specifically, we innovatively incorporate multitemporal, high-resolution RS image data into a unified KG framework endowed with spatio-temporal evolution properties. By representing image features within a KG structure, this approach not only improves the efficiency of spatio-temporal data management, but also enhances the applicability of large language model (LLM) in the domain-specific context of RS. Experimental results demonstrate that integrating RS imagery, geographic information, and domain expertise into a structured and evolvable knowledge system significantly strengthens the semantic expressiveness of RS data. Furthermore, it enables LLMs to better interpret spatial semantics, accurately analyze surface change dynamics.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"7341-7356"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358954","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299633","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}
Infrared imaging plays a crucial role in applications, such as search-and-rescue operations and fire monitoring, due to its robustness under complex environmental conditions. Nevertheless, the inherent low spatial resolution of infrared cameras, and the complicated imaging degradation process, still constrains the quality of captured images, thereby posing challenges for downstream tasks. Existing infrared image super-resolution methods (e.g., diffusion-based methods) often neglect the unique modality characteristics of infrared images and fail to effectively introduce additional fine-grained information. To address these limitations, we propose a novel framework named Visible-light-guided infrared image super resolution with dual amplitude-phase optimization (vap-SR). By leveraging the powerful generative capability of conditional diffusion and fully exploiting the rich structural priors embedded in visible images, vap-SR effectively compensates for the deficiencies of infrared images in terms of details, thereby overcoming the inherent limitations in texture fidelity. Phase and amplitude losses are designed to preserve the physical characteristics of the infrared modality while effectively leveraging the structural information from visible-light images. Extensive experiments demonstrate that vap-SR consistently outperforms state-of-the-art methods in both reconstruction quality and downstream object detection task, validating its effectiveness for infrared super resolution.
{"title":"Visible-Light-Guided Infrared Image Super Resolution With Dual Amplitude-Phase Optimization","authors":"Qingwang Wang;Yuhang Wu;Pengcheng Jin;Yan Lin;Zhen Zhang;Tao Shen","doi":"10.1109/JSTARS.2026.3655485","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655485","url":null,"abstract":"Infrared imaging plays a crucial role in applications, such as search-and-rescue operations and fire monitoring, due to its robustness under complex environmental conditions. Nevertheless, the inherent low spatial resolution of infrared cameras, and the complicated imaging degradation process, still constrains the quality of captured images, thereby posing challenges for downstream tasks. Existing infrared image super-resolution methods (e.g., diffusion-based methods) often neglect the unique modality characteristics of infrared images and fail to effectively introduce additional fine-grained information. To address these limitations, we propose a novel framework named Visible-light-guided infrared image super resolution with dual amplitude-phase optimization (vap-SR). By leveraging the powerful generative capability of conditional diffusion and fully exploiting the rich structural priors embedded in visible images, vap-SR effectively compensates for the deficiencies of infrared images in terms of details, thereby overcoming the inherent limitations in texture fidelity. Phase and amplitude losses are designed to preserve the physical characteristics of the infrared modality while effectively leveraging the structural information from visible-light images. Extensive experiments demonstrate that vap-SR consistently outperforms state-of-the-art methods in both reconstruction quality and downstream object detection task, validating its effectiveness for infrared super resolution.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5774-5784"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358958","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175754","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655359
Jianing Shao;Yanlei Du;Xiaofeng Yang;Longxiang Linghu;Jinsong Chong;Jian Yang
This study numerically investigates the spatial ergodicity of Doppler characteristics in polarimetric ocean radar scattering. The full Apel wave spectrum is employed to generate 2-D time-varying sea surfaces that involve all dominant large-scale gravity waves and small-scale capillary waves. By solving the radar scattering from time-varying ocean surfaces with various illumination sizes using the second-order small-slope approximation (SSA-2) model, the Doppler spectra, along with the Doppler shift and width, are thus computed and analyzed. The numerical simulations are conducted at L-band for three typical fully developed sea states. A Doppler shift error threshold is defined based on the accuracy requirements of sea surface current retrieval, and the spatial ergodicity of Doppler shift is evaluated quantitatively. Simulation results indicate that under co-polarization, the Doppler shift manifests spatial ergodicity when the sea surface size illuminated by radar is no less than one-quarter of the largest gravity wave wavelength at the corresponding sea state. For cross-polarization, the spatial ergodicity of the Doppler shift is significantly reduced and is observed only when the illumination size exceeds about one-half of the largest gravity wave wavelength. The results also indicate that wind direction has a limited effect on the spatial ergodicity of the Doppler shift.
{"title":"Spatial Ergodicity of Doppler Characteristics in Polarimetric Ocean Radar Scattering: A Numerical Study","authors":"Jianing Shao;Yanlei Du;Xiaofeng Yang;Longxiang Linghu;Jinsong Chong;Jian Yang","doi":"10.1109/JSTARS.2026.3655359","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655359","url":null,"abstract":"This study numerically investigates the spatial ergodicity of Doppler characteristics in polarimetric ocean radar scattering. The full Apel wave spectrum is employed to generate 2-D time-varying sea surfaces that involve all dominant large-scale gravity waves and small-scale capillary waves. By solving the radar scattering from time-varying ocean surfaces with various illumination sizes using the second-order small-slope approximation (SSA-2) model, the Doppler spectra, along with the Doppler shift and width, are thus computed and analyzed. The numerical simulations are conducted at L-band for three typical fully developed sea states. A Doppler shift error threshold is defined based on the accuracy requirements of sea surface current retrieval, and the spatial ergodicity of Doppler shift is evaluated quantitatively. Simulation results indicate that under co-polarization, the Doppler shift manifests spatial ergodicity when the sea surface size illuminated by radar is no less than one-quarter of the largest gravity wave wavelength at the corresponding sea state. For cross-polarization, the spatial ergodicity of the Doppler shift is significantly reduced and is observed only when the illumination size exceeds about one-half of the largest gravity wave wavelength. The results also indicate that wind direction has a limited effect on the spatial ergodicity of the Doppler shift.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5493-5506"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358708","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175824","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655550
Ch Muhammad Awais;Marco Reggiannini;Davide Moroni;Oktay Karakus
High-resolution imagery plays a critical role in improving the performance of visual recognition tasks such as classification, detection, and segmentation. In many domains, including remote sensing and surveillance, low-resolution images can limit the accuracy of automated analysis. To address this, superresolution techniques have been widely adopted to attempt to reconstruct high-resolution images from low-resolution inputs. Related traditional approaches focus solely on enhancing image quality based on pixel-level metrics, leaving the relationship between superresolved image fidelity and downstream classification performance largely underexplored. This raises a key question: Can integrating classification objectives directly into the superresolution process further improve classification accuracy? In this article, we try to respond to this question by investigating the relationship between superresolution and classification through the deployment of a specialized algorithmic strategy. We propose a novel methodology that increases the resolution of synthetic aperture radar imagery by optimizing loss functions that account for both image quality and classification performance. Our approach improves image quality, as measured by scientifically ascertained image quality indicators, while also enhancing classification accuracy.
{"title":"A Classification-Aware Superresolution Framework for Ship Targets in SAR Imagery","authors":"Ch Muhammad Awais;Marco Reggiannini;Davide Moroni;Oktay Karakus","doi":"10.1109/JSTARS.2026.3655550","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655550","url":null,"abstract":"High-resolution imagery plays a critical role in improving the performance of visual recognition tasks such as classification, detection, and segmentation. In many domains, including remote sensing and surveillance, low-resolution images can limit the accuracy of automated analysis. To address this, superresolution techniques have been widely adopted to attempt to reconstruct high-resolution images from low-resolution inputs. Related traditional approaches focus solely on enhancing image quality based on pixel-level metrics, leaving the relationship between superresolved image fidelity and downstream classification performance largely underexplored. This raises a key question: Can integrating classification objectives directly into the superresolution process further improve classification accuracy? In this article, we try to respond to this question by investigating the relationship between superresolution and classification through the deployment of a specialized algorithmic strategy. We propose a novel methodology that increases the resolution of synthetic aperture radar imagery by optimizing loss functions that account for both image quality and classification performance. Our approach improves image quality, as measured by scientifically ascertained image quality indicators, while also enhancing classification accuracy.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"6614-6622"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358667","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223541","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655410
Meisam Shayegh Moradi;Kyle Foerster;Naima Kaabouch;Sheridan Parker;Aymane Ahajjam;Andrew Wilcox;Timothy J. Pasch
This paper introduces a high performance, distributed Artificial Intelligence (AI) based data processing architecture for Arctic multivariate geospatial feature prediction, designed to enhance heterogeneous weather modeling and support broader world scale simulations. The framework was validated on a 25 year Alaska air temperature dataset. The workflow partitions the dataset into spatio-temporally independent chunks, which are preprocessed and scored locally. Feature scores are then aggregated through a weighted voting mechanism, emphasizing predictors that remain consistently influential across diverse regions. This approach captures locally significant patterns while preserving their relevance in a broader global context, ensuring both regional detail and global coherence. Distributed data processing reduces computation time, improves model accuracy, and enhances generalization across heterogeneous Arctic landscapes. Eight feature selection techniques, including filter, wrapper, and embedded methods, were evaluated for predictor relevance and computational efficiency across distributed partitions. Four AI models spanning linear, non-linear, time series machine learning, and non-time series deep learning were trained on regionally diverse datasets to predict air temperature. Model performance was evaluated using MSE, sMAPE, KGE and MPE (%). Results indicate that distributed processing accelerates computation while achieving predictive performance equal to or better than serial methods. Techniques such as Kendall+DT and Pearson+MI demonstrate strong scalability with increasing dataset size and computational resources, highlighting their suitability for large scale Arctic datasets and integration into comprehensive global modeling frameworks. By capturing localized geophysical patterns and aggregating them globally, this approach enables more accurate and robust Arctic weather prediction and provides a foundation for broader world modeling applications.
{"title":"High Performance Distributed Data Processing Architecture for AI-Based Multivariate Arctic Geospatial Predictive Weather Modeling","authors":"Meisam Shayegh Moradi;Kyle Foerster;Naima Kaabouch;Sheridan Parker;Aymane Ahajjam;Andrew Wilcox;Timothy J. Pasch","doi":"10.1109/JSTARS.2026.3655410","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655410","url":null,"abstract":"This paper introduces a high performance, distributed Artificial Intelligence (AI) based data processing architecture for Arctic multivariate geospatial feature prediction, designed to enhance heterogeneous weather modeling and support broader world scale simulations. The framework was validated on a 25 year Alaska air temperature dataset. The workflow partitions the dataset into spatio-temporally independent chunks, which are preprocessed and scored locally. Feature scores are then aggregated through a weighted voting mechanism, emphasizing predictors that remain consistently influential across diverse regions. This approach captures locally significant patterns while preserving their relevance in a broader global context, ensuring both regional detail and global coherence. Distributed data processing reduces computation time, improves model accuracy, and enhances generalization across heterogeneous Arctic landscapes. Eight feature selection techniques, including filter, wrapper, and embedded methods, were evaluated for predictor relevance and computational efficiency across distributed partitions. Four AI models spanning linear, non-linear, time series machine learning, and non-time series deep learning were trained on regionally diverse datasets to predict air temperature. Model performance was evaluated using MSE, sMAPE, KGE and MPE (%). Results indicate that distributed processing accelerates computation while achieving predictive performance equal to or better than serial methods. Techniques such as Kendall+DT and Pearson+MI demonstrate strong scalability with increasing dataset size and computational resources, highlighting their suitability for large scale Arctic datasets and integration into comprehensive global modeling frameworks. By capturing localized geophysical patterns and aggregating them globally, this approach enables more accurate and robust Arctic weather prediction and provides a foundation for broader world modeling applications.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"7627-7643"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358670","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299579","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655376
Haiwei Yu;Huapeng Li;Jian Lu;Tongtong Zhao;Baoqi Liu
Accurate crop yield estimation is essential for global food security, especially high-resolution mapping that supports field-scale management and detailed yield gap analysis. This study developed a hybrid yield estimation framework, named ensemble Kalman filter-random forest (EnKF-RF), which coupled data assimilation with a two-stage random forest approach. In this framework, Sentinel-2-derived leaf area index was first assimilated into the WOrld FOod Studies model using the EnKF algorithm. An RF-based metamodel (RF_SIM) was then trained to approximate the assimilation process, followed by a second RF model (RF_FIELD) that integrated land surface phenology, extreme-climate indicators, and limited ground observations to estimate crop yield. The proposed framework was applied to maize yield estimation in Jilin Province, China, during 2022–2024. The results showed that EnKF-RF achieved superior performance [R 2 = 0.476, root-mean-square error (RMSE) = 1565.87 kg/ha, and mean absolute error (MAE) = 1299.42 kg/ha] compared with a standalone random forest (R 2 = 0.394, RMSE = 1685.04 kg/ha, and MAE = 1428.69 kg/ha) and the scalable crop yield mapper approach. Furthermore, the implementation of the metamodel substantially enhanced the efficiency of the EnKF-RF framework, allowing annual maize yield estimation to be achieved within 18 min per 10 000 km2 in Jilin Province when utilizing Google Earth Engine. Water availability was identified as the primary driver of interannual yield variability, especially due to spring drought and the co-occurrence of water stress and waterlogging during July and August according to the SHapley Additive exPlanations. Generally, EnKF-RF provides a scalable and efficient solution for high-resolution maize yield mapping, particularly in data-scarce regions.
{"title":"Metamodel-Accelerated High-Resolution Maize Yield Mapping via Sentinel-2 Assimilation and Random Forest","authors":"Haiwei Yu;Huapeng Li;Jian Lu;Tongtong Zhao;Baoqi Liu","doi":"10.1109/JSTARS.2026.3655376","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655376","url":null,"abstract":"Accurate crop yield estimation is essential for global food security, especially high-resolution mapping that supports field-scale management and detailed yield gap analysis. This study developed a hybrid yield estimation framework, named ensemble Kalman filter-random forest (EnKF-RF), which coupled data assimilation with a two-stage random forest approach. In this framework, Sentinel-2-derived leaf area index was first assimilated into the WOrld FOod Studies model using the EnKF algorithm. An RF-based metamodel (RF_SIM) was then trained to approximate the assimilation process, followed by a second RF model (RF_FIELD) that integrated land surface phenology, extreme-climate indicators, and limited ground observations to estimate crop yield. The proposed framework was applied to maize yield estimation in Jilin Province, China, during 2022–2024. The results showed that EnKF-RF achieved superior performance [<italic>R</i> <sup>2</sup> = 0.476, root-mean-square error (RMSE) = 1565.87 kg/ha, and mean absolute error (MAE) = 1299.42 kg/ha] compared with a standalone random forest (<italic>R</i> <sup>2</sup> = 0.394, RMSE = 1685.04 kg/ha, and MAE = 1428.69 kg/ha) and the scalable crop yield mapper approach. Furthermore, the implementation of the metamodel substantially enhanced the efficiency of the EnKF-RF framework, allowing annual maize yield estimation to be achieved within 18 min per 10 000 km<sup>2</sup> in Jilin Province when utilizing Google Earth Engine. Water availability was identified as the primary driver of interannual yield variability, especially due to spring drought and the co-occurrence of water stress and waterlogging during July and August according to the SHapley Additive exPlanations. Generally, EnKF-RF provides a scalable and efficient solution for high-resolution maize yield mapping, particularly in data-scarce regions.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"6341-6358"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358689","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223627","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655350
Wenjing Li;Libin Du;Xinglei Zhao
Accurate water-land classification is fundamental for topographic mapping and coastal zone monitoring based on airborne LiDAR bathymetry (ALB). However, due to the limited information content and feature ambiguity of one-dimensional (1-D) waveform signals, accurate classification from single-wavelength ALB data remains challenging. To address this issue, a dual-branch multimodal fusion network (CRMF-Net) is proposed to improve both classification accuracy and robustness. The proposed network consists of a convolutional neural network (CNN) branch and a convolutional block attention module optimized residual neural network branch, which are designed to capture complementary temporal and spatial features, respectively. The 1-D green waveform is converted into a 2-D time-frequency representation through the continuous wavelet transform, thereby increasing the dimensions and quantity of waveform features. By jointly exploiting complementary information from waveform signals and their corresponding time–frequency representations, the proposed method enables more effective feature representation without relying on extensive handcrafted analysis. Experiments conducted on CZMIL datasets from Qinshan Island demonstrate that CRMF-Net achieves an overall accuracy of 97.33% with a kappa coefficient of 0.9168, outperforming traditional methods, such as fuzzy C-means, support vector machine, and the one-dimensional convolutional neural network approach. These results indicate that the proposed method provides a promising solution for fully automated processing of single-wavelength ALB data.
{"title":"CRMF-Net: A Multimodal Fusion Network for Water–Land Classification From Single-Wavelength Bathymetric LiDAR","authors":"Wenjing Li;Libin Du;Xinglei Zhao","doi":"10.1109/JSTARS.2026.3655350","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655350","url":null,"abstract":"Accurate water-land classification is fundamental for topographic mapping and coastal zone monitoring based on airborne LiDAR bathymetry (ALB). However, due to the limited information content and feature ambiguity of one-dimensional (1-D) waveform signals, accurate classification from single-wavelength ALB data remains challenging. To address this issue, a dual-branch multimodal fusion network (CRMF-Net) is proposed to improve both classification accuracy and robustness. The proposed network consists of a convolutional neural network (CNN) branch and a convolutional block attention module optimized residual neural network branch, which are designed to capture complementary temporal and spatial features, respectively. The 1-D green waveform is converted into a 2-D time-frequency representation through the continuous wavelet transform, thereby increasing the dimensions and quantity of waveform features. By jointly exploiting complementary information from waveform signals and their corresponding time–frequency representations, the proposed method enables more effective feature representation without relying on extensive handcrafted analysis. Experiments conducted on CZMIL datasets from Qinshan Island demonstrate that CRMF-Net achieves an overall accuracy of 97.33% with a kappa coefficient of 0.9168, outperforming traditional methods, such as fuzzy C-means, support vector machine, and the one-dimensional convolutional neural network approach. These results indicate that the proposed method provides a promising solution for fully automated processing of single-wavelength ALB data.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5804-5813"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358398","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175694","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}
Pub Date : 2026-01-19DOI: 10.1109/JSTARS.2026.3655144
Marta Alonso Tubía;Miguel Baena Botana;An Vo Quang;Ana Burgin;Oliva Garcia Cantú-Ros
Dynamic population mapping has become crucial for capturing real-time human movement and behavior, beyond traditional population mapping relying on census data. Differentiating indoor and outdoor activity enhances accuracy for smart city planning, emergency response, public health, or emerging technologies like Innovative Air Mobility, where pedestrian data informs safer, less disruptive flight planning. Data passively collected from mobile networks have proven to be highly effective in accurately capturing population presence and mobility patterns. By enhancing this rich data source with GPS data for spatial accuracy and validating the results with satellite imagery of detected pedestrians, we provide a procedure for indoor and outdoor population detection. The results show agreement between both methodologies. Despite some limitations related to GPS data biases and pedestrian detection issues caused by urban furniture and shadows, the procedure demonstrates strong potential to capture people’s movements, which could ultimately enable near real-time monitoring of population presence on the streets.
{"title":"Toward Outdoor Population Presence Monitoring With Mobile Network Data and Satellite Imagery","authors":"Marta Alonso Tubía;Miguel Baena Botana;An Vo Quang;Ana Burgin;Oliva Garcia Cantú-Ros","doi":"10.1109/JSTARS.2026.3655144","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3655144","url":null,"abstract":"Dynamic population mapping has become crucial for capturing real-time human movement and behavior, beyond traditional population mapping relying on census data. Differentiating indoor and outdoor activity enhances accuracy for smart city planning, emergency response, public health, or emerging technologies like Innovative Air Mobility, where pedestrian data informs safer, less disruptive flight planning. Data passively collected from mobile networks have proven to be highly effective in accurately capturing population presence and mobility patterns. By enhancing this rich data source with GPS data for spatial accuracy and validating the results with satellite imagery of detected pedestrians, we provide a procedure for indoor and outdoor population detection. The results show agreement between both methodologies. Despite some limitations related to GPS data biases and pedestrian detection issues caused by urban furniture and shadows, the procedure demonstrates strong potential to capture people’s movements, which could ultimately enable near real-time monitoring of population presence on the streets.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5834-5852"},"PeriodicalIF":5.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11358662","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175807","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：