ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"Multimodal remote sensing change detection: An image matching perspective","authors":"Hongruixuan Chen ,&nbsp;Cuiling Lan ,&nbsp;Jian Song ,&nbsp;Damian Ibañez ,&nbsp;Junshi Xia ,&nbsp;Konrad Schindler ,&nbsp;Naoto Yokoya","doi":"10.1016/j.isprsjprs.2026.02.004","DOIUrl":"10.1016/j.isprsjprs.2026.02.004","url":null,"abstract":"<div><div>Change Detection (CD) between images with different modalities is a fundamental capability for remote sensing. In this work, we pinpoint the commonalities between Multimodal Change Detection (MCD) and Multimodal Image Matching (MIM). Accordingly, we present a new unsupervised CD framework designed from the perspective of Image Matching (IM), called IM4CD. It unifies the IM and CD tasks into a single, coherent framework. In this framework, we abandon the prevalent strategy in MCD to compare per-pixel image features, since it is in practice quite difficult to design features that are truly invariant across modalities. Instead, we propose to compute similarity by local template matching and utilize the spatial offset of response peaks to represent change intensity between images with different modalities, and then to integrate it tightly with the co-registration of the two images, which anyway includes such a matching step. In this way, the same off-the-shelf descriptors used for MIM also support MCD. In other words, we first extract modality-independent features, then detect salient points to obtain initial pairs of corresponding Control Points (CP). When matching those points to accurately register the images, CP pairs located in unchanged areas show low residuals, whereas those in changed areas show high residuals. The CPs can then be connected into a Conditional Random Field (CRF), leveraging modality-independent structural relationships to estimate dense change maps. Experimental results show the effectiveness of our method, including robustness to registration errors, its compatibility with different image descriptors, and promising potential for challenging real-world disaster response scenarios.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 487-501"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MMP-Mapper: Multi-modal priors enhancing vectorized HD road map construction from aerial imagery","authors":"Haofeng Xie ,&nbsp;Huiwei Jiang ,&nbsp;Yandi Yang ,&nbsp;Xiangyun Hu","doi":"10.1016/j.isprsjprs.2026.02.008","DOIUrl":"10.1016/j.isprsjprs.2026.02.008","url":null,"abstract":"<div><div>High-definition (HD) road maps are indispensable for autonomous driving, supporting tasks such as localization, planning, and navigation. The traditional construction of HD road maps heavily relies on manual annotation of data from LiDAR, cameras, and GPS/IMU, a process that is both costly and time-consuming. While recent work has explored automatic HD road map extraction from aerial imagery — a data source offering broad-area coverage and superior robustness — existing methods face a critical limitation. They often process only a single, isolated image tile, failing to leverage crucial spatial context and semantic priors from multi-modal data sources. This shortage severely impacts map accuracy and continuity, especially at complex intersections and in occluded areas. To overcome these challenges, we propose MMP-Mapper, a novel framework that enhances HD road map construction with multi-modal priors. MMP-Mapper introduces two key modules: (1) the Contextual Image Fusion (CIF) module, which selects and fuses features from neighbor image tiles to provide spatial continuity; and (2) the Map-Guided Fusion (MGF) module, which uses a Transformer module to fuse the encoded semantic attributes from standard-definition (SD) road maps with geometric priors, guiding HD road map construction. We validate our framework on the Aerial Argoverse 2 and OpenSatMap datasets. Our results demonstrate that MMP-Mapper outperforms state-of-the-art baselines in both accuracy and generalization for aerial-imagery-based HD road map construction.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 543-555"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Satellite-based heat Index estimatioN modEl (SHINE): An integrated machine learning approach for the conterminous United States","authors":"Seyed Babak Haji Seyed Asadollah,&nbsp;Giorgos Mountrakis,&nbsp;Stephen B. Shaw","doi":"10.1016/j.isprsjprs.2026.01.018","DOIUrl":"10.1016/j.isprsjprs.2026.01.018","url":null,"abstract":"<div><div>The accelerating frequency, duration and intensity of extreme heat events demand accurate, spatially complete heat exposure metrics. Here, a modeling approach is presented for estimating the daily-maximum Heat Index (HI) at 1 km spatial resolution. Our study area covered the conterminous United States (CONUS) during the warm season (May to September) between 2003 and 2023. More than 4.6 million observations from approximately 2000 weather stations were paired with weather-related, geographical, land cover and historical climatic factors to develop the proposed Satellite-based Heat Index estimatioN modEl (SHINE). Selected explanatory variables at daily temporal intervals included reanalysis products from Modern-Era Retrospective analysis for Research and Applications (MERRA) and direct satellite products from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor.</div><div>The most influential variables for HI estimation were the MERRA surface layer height and specific humidity products and the dual-pass MODIS daily land surface temperatures. These were followed by land cover products capturing water and forest presence, historical norms of wind speed and maximum temperature, elevation information and the corresponding day of year. An Extreme Gradient Boosting (XGBoost) regressor trained with spatial cross-validation explained 93 % of the variance (R² = 0.93) and attained a Root Mean Square Error (RMSE) of 1.9°C and a Mean Absolute Error (MAE) of 1.4°C. Comparison of alternative configurations showed that while a MERRA-only model provided slightly higher accuracy (RMSE of 1.8°C), its coarse resolution failed to capture fine-scale heat variations. Conversely, a MODIS-only model offered kilometer-scale spatial resolution but with higher estimation errors (RMSE of 2.9°C). Integrating both MERRA and MODIS sources enabled SHINE to maintain spatial detail and preserved accuracy, underscoring the complementary strengths of reanalysis and satellite products. SHINE also demonstrated resistance to missing MODIS LST observations due to clouds as the additional RMSE error was approximately 0.5°C in the worst case of missing both morning and afternoon MODIS land surface temperature observations. Spatial error analysis revealed &lt;1.7°C RMSE in arid and Mediterranean zones but larger, more heterogeneous errors in the humid Midwest and High Plains. From the policy perspective and considering the HI operational range for public-health heat effects, the proposed SHINE approach outperformed typically used proxies, such as land surface and air temperature. The resulting 1 km daily HI estimations can potentially be used as the foundation of the first wall-to-wall, multi-decadal, high resolution heat dataset for CONUS and offer actionable information for public-health heat studies, energy-demand forecasting and environmental-justice implications.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 209-230"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing conditional generative adversarial networks for SAR-to-optical image translation via auxiliary geospatial landscape pattern-augmentation","authors":"Hongbo Liang ,&nbsp;Xuezhi Yang ,&nbsp;Xiangyu Yang ,&nbsp;Xin Jing","doi":"10.1016/j.isprsjprs.2026.01.043","DOIUrl":"10.1016/j.isprsjprs.2026.01.043","url":null,"abstract":"<div><div>Synthetic aperture radar (SAR) enables all-weather, all-day Earth observation, yet speckle noise and geometric distortions from complex electromagnetic scattering imaging severely limit its visual interpretability. SAR-to-optical image translation (S2OIT) has emerged to mitigate these challenges, but remains hindered by the data heterogeneity and spectral discrepancies between SAR and optical domains, where integrating auxiliary knowledge offers a viable remedy. What is more, previous studies rely on a pixel-wise constrained adversarial learning paradigm with limited mining of geospatial landscape information are prone to generating low-fidelity images. To tackle these issues, we propose AGPA-CGAN, a conditional generative adversarial network (CGAN) framework with auxiliary geospatial landscape pattern-augmentation for high-quality S2OIT. AGPA-CGAN progressively narrows the gap between translated and reference images by integrating ample SAR prior properties and geospatial structural information from scenario image pairs into the S2OIT process. Specifically, to fully exploit the tremendous priors of SAR images, we design an auxiliary pseudo-scattering pattern integration (APSPI) module to extract hierarchical subspace frequency conditional representations, thereby aiding AGPA-CGAN in capturing more descriptive cues for S2OIT. In particular, we introduce an unsupervised subspace embedding clustering (SEC) algorithm based on subspace frequency analysis (SSFA) within APSPI to derive statistical pseudo-scattering behavior maps against SAR feature spectrums. Furthermore, to stabilize the integration of SAR priors, we propose a geospatial landscape domain alignment (Geo-LDA) module that applies multi-perspective consistency regularization to align structural correspondences between SAR and optical features. Extensive experiments on three challenging benchmarks demonstrate that AGPA-CGAN surpasses state-of-the-art (SOTA) methods in both translation fidelity and structural realism.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 502-518"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"WHU-STree: A multi-modal benchmark dataset for street tree inventory","authors":"Ruifei Ding ,&nbsp;Zhe Chen ,&nbsp;Wen Fan ,&nbsp;Chen Long ,&nbsp;Huijuan Xiao ,&nbsp;Yelu Zeng ,&nbsp;Zhen Dong ,&nbsp;Bisheng Yang","doi":"10.1016/j.isprsjprs.2026.02.011","DOIUrl":"10.1016/j.isprsjprs.2026.02.011","url":null,"abstract":"<div><div>Street trees are vital to urban livability, providing ecological and social benefits. Establishing a detailed, accurate, and dynamically updated street tree inventory has become essential for optimizing these multifunctional assets within space-constrained urban environments. Given that traditional field surveys are time-consuming and labor-intensive, automated surveys utilizing Mobile Mapping Systems (MMS) offer a more efficient solution. However, existing MMS-acquired tree datasets are limited by small-scale scene, limited annotation, or single modality, restricting their utility for comprehensive analysis. To address these limitations, we introduce WHU-STree, a cross-city, richly annotated, and multi-modal urban street tree dataset. Collected across two distinct cities, WHU-STree integrates synchronized point clouds and high-resolution images, encompassing 21,007 annotated tree instances across 50 species and 2 morphological parameters. Leveraging the unique characteristics, WHU-STree concurrently supports over 10 tasks related to street tree inventory. We benchmark representative baselines for two key tasks—tree species classification and individual tree segmentation—based on 18 major species and an “Others” category. Extensive experiments demonstrate that while multi-modal fusion yields improvements over uni-modal baselines, it currently presents performance gaps compared to strong 3D-only methods, indicating that effective fusion remains a challenging open problem requiring further research. In particular, we identify key challenges and outline potential future works for fully exploiting WHU-STree, encompassing multi-modal fusion, multi-task collaboration, cross-domain generalization, spatial pattern learning, and Multi-modal Large Language Model for street tree asset management. The WHU-STree dataset is accessible at: <span><span>https://github.com/WHU-USI3DV/WHU-STree</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 519-542"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EAV-DETR: Efficient Arbitrary-View oriented object detection with probabilistic guarantees for UAV imagery","authors":"Haoyu Zuo ,&nbsp;Minghao Ning ,&nbsp;Yiming Shu ,&nbsp;Shucheng Huang ,&nbsp;Chen Sun","doi":"10.1016/j.isprsjprs.2026.02.009","DOIUrl":"10.1016/j.isprsjprs.2026.02.009","url":null,"abstract":"<div><div>Oriented object detection is critical for enhancing the visual perception of unmanned aerial vehicles (UAVs). However, existing detectors primarily designed for general aerial imagery often struggle to address the unique challenges of UAV imagery, including substantial scale variations, dense clustering, and arbitrary orientations. Furthermore, these models lack probabilistic guarantees required for safety-critical applications. To address these challenges, we propose EAV-DETR, an efficient oriented object detection transformer designed for UAV imagery. Specifically, we first propose a novel scale-adaptive center supervision (SACS) strategy that explicitly enhances the encoder’s feature representations by imposing pixel-level localization constraints with zero inference overhead. Second, we design an anisotropic decoupled rotational attention (ADRA) module, which achieves superior feature alignment for objects of arbitrary morphology by generating a non-rigid adaptive sampling field. Finally, we propose a pose-aware Mondrian conformal prediction (PA-MCP) method, which utilizes the UAV’s flight pose as a physical prior to generate prediction sets with conditional coverage guarantees, thereby providing reliable uncertainty quantification. Extensive experiments on multiple aerial imagery datasets validate the effectiveness of our model. Compared to previous state-of-the-art methods, EAV-DETR improves <span><math><msub><mrow><mtext>AP</mtext></mrow><mrow><mn>75</mn></mrow></msub></math></span> on CODrone by 1.76% while achieving a 52% faster inference speed (46.38 vs 30.55 FPS), and improves <span><math><msub><mrow><mtext>AP</mtext></mrow><mrow><mn>50</mn><mo>:</mo><mn>95</mn></mrow></msub></math></span> on UAV-ROD by 3.17%. Our code is available at <span><span>https://github.com/zzzhak/EAV-DETR</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 575-587"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RegScorer: Learning to select the best transformation of point cloud registration","authors":"Xiaochen Yang ,&nbsp;Haiping Wang ,&nbsp;Yuan Liu ,&nbsp;Bisheng Yang ,&nbsp;Zhen Dong","doi":"10.1016/j.isprsjprs.2026.01.034","DOIUrl":"10.1016/j.isprsjprs.2026.01.034","url":null,"abstract":"<div><div>We propose RegScorer, a model learning to identify the optimal transformation to register unaligned point clouds. Existing registration advancements can generate a set of candidate transformations, which are then evaluated using conventional metrics such as Inlier Ratio (IR), Mean Squared Error (MSE) or Chamfer Distance (CD). The candidate achieving the best score is selected as the final result. However, we argue that these metrics often fail to select the correct transformation, especially in challenging scenarios involving symmetric objects, repetitive structures, or low-overlap regions. This leads to significant degradation in registration performance, a problem that has long been overlooked. The core issue lies in their limited focus on local geometric consistency and inability to capture two key conflict cases of misalignment: (1) point pairs that are spatially close after alignment but have conflicting features, and (2) point pairs with high feature similarity but large spatial distances after alignment. To address this, we propose RegScorer, which models both the spatial and feature relationships of all point pairs. This allows RegScorer to learn to capture the above conflict cases and provides a more reliable score for transformation quality. On the 3DLoMatch and ScanNet datasets, RegScorer demonstrate <strong>19.3</strong>% and <strong>14.1</strong>% improvements in registration recall, leading to <strong>4.7</strong>% and <strong>5.1</strong>% accuracy gains in multiview registration. Moreover, when generalized to symmetric and low-texture outdoor scenes, RegScorer achieves a <strong>25</strong>% increase in transformation recall over IR metric, highlighting its robustness and generalizability. The pre-trained model and the complete code repository can be accessed at <span><span>https://github.com/WHU-USI3DV/RegScorer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 266-277"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"VectorLLM: Human-like extraction of structured building contours via multimodal LLMs","authors":"Tao Zhang ,&nbsp;Shiqing Wei ,&nbsp;Shihao Chen ,&nbsp;Wenling Yu ,&nbsp;Muying Luo ,&nbsp;Shunping Ji","doi":"10.1016/j.isprsjprs.2026.01.025","DOIUrl":"10.1016/j.isprsjprs.2026.01.025","url":null,"abstract":"<div><div>Automatically extracting vectorized building contours from remote sensing imagery is crucial for urban planning, population estimation, and disaster assessment. Current state-of-the-art methods rely on complex multi-stage pipelines involving pixel segmentation, vectorization, and polygon refinement, which limits their scalability and real-world applicability. Inspired by the remarkable reasoning capabilities of Large Language Models (LLMs), we introduce VectorLLM, the first Multi-modal Large Language Model (MLLM) designed for regular building contour extraction from remote sensing images. Unlike existing approaches, VectorLLM performs corner-point by corner-point regression of building contours directly, mimicking human annotators’ labeling process. Our architecture consists of a vision foundation backbone, an MLP connector, and an LLM, enhanced with learnable position embeddings to improve spatial understanding capability. Through comprehensive exploration of training strategies including pretraining, supervised fine-tuning, and direct preference optimization across WHU, WHU-Mix, and CrowdAI datasets, VectorLLM outperforms the previous SOTA methods. Remarkably, VectorLLM exhibits strong zero-shot performance on unseen objects including aircraft, water bodies, and oil tanks, highlighting its potential for unified modeling of diverse remote sensing object contour extraction tasks. Overall, this work establishes a new paradigm for vector extraction in remote sensing, leveraging the topological reasoning capabilities of LLMs to achieve both high accuracy and exceptional generalization. All code and weights will be available at <span><span>https://github.com/zhang-tao-whu/VectorLLM</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 55-68"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-object tracking of vehicles and anomalous states in remote sensing videos: Joint learning of historical trajectory guidance and ID prediction","authors":"Bin Wang ,&nbsp;Yuan Zhou ,&nbsp;Haigang Sui ,&nbsp;Guorui Ma ,&nbsp;Peng Cheng ,&nbsp;Di Wang","doi":"10.1016/j.isprsjprs.2026.01.038","DOIUrl":"10.1016/j.isprsjprs.2026.01.038","url":null,"abstract":"<div><div>Research on multi-object tracking (MOT) of vehicles based on remote sensing video data has achieved breakthrough progress. However, MOT of vehicles in complex scenarios and their anomalous states after being subjected to strong deformation interference remains a huge challenge. This is of great significance for military defense, traffic flow management, vehicle damage assessment, etc. To address this problem, this study proposes an end-to-end MOT method that integrates a joint learning paradigm of historical trajectory guidance and identity (ID) prediction, aiming to bridge the gap between vehicle detection and continuous tracking after anomalous states occurrence. The proposed network framework primarily consists of a Frame Feature Aggregation Module (FFAM) that enhances spatial consistency of objects across consecutive video frames, a Historical Tracklets Flow Encoder (HTFE) that employs Mamba blocks to guide object embedding within potential motion flows based on historical frames, and a Semantic-Consistent Clustering Module (SCM) constructed via sparse attention computation to capture global semantic information. The discriminative features extracted by these modules are fused by a Dual-branch Modulation Fusion Unit (DMFU) to maximize the performance of the model. This study also constructs a new dataset for MOT of vehicles and anomalous states in videos, termed the VAS-MOT dataset. Extensive validation experiments conducted on this dataset demonstrate that the method achieves the highest level of performance, with HOTA and MOTA reaching 68.2% and 71.5%, respectively. Additional validation on the open-source dataset IRTS-AG confirms the strong robustness of the proposed method, showing excellent performance in long-term tracking of small vehicles in infrared videos under complex scenarios, where HOTA and MOTA reached 70.9% and 91.6%, respectively. The proposed method provides valuable insights for capturing moving objects and their anomalous states, laying a foundation for further damage assessment.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 383-406"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel transformer-based CO2 retrieval framework incorporating prior constraint and hierarchical features injection: assessment of transferability for Tansat-2","authors":"Lingfeng Zhang ,&nbsp;Lu Zhang ,&nbsp;Xingying Zhang ,&nbsp;Tiantao Cheng ,&nbsp;Xifeng Cao ,&nbsp;Tongwen Li ,&nbsp;Dongdong Liu ,&nbsp;Yang Zhang ,&nbsp;Yuhan Jiang ,&nbsp;Ruohua Hu ,&nbsp;Haiyang Dou ,&nbsp;Lin Chen","doi":"10.1016/j.isprsjprs.2026.01.039","DOIUrl":"10.1016/j.isprsjprs.2026.01.039","url":null,"abstract":"<div><div>Carbon dioxide (CO₂), the primary contributor to global warming, significantly impacts global climate change. Remote sensing is an effective approach for monitoring atmospheric CO₂ concentrations. However, the commonly used satellite’s full-physics Optimal Estimation (OE) method is time-consuming and requires advanced equipment. Additionally, traditional deep learning algorithms for satellite CO₂ retrieval suffer from limitations in accuracy and an inability to extrapolate effectively to unseen high values, caused by the gradually increasing concentrations over time. Balancing both efficiency and extrapolation capabilities is a critical task, especially for the next generation of large-swath carbon satellite with a significant increase in data volumes, such as Tansat-2. In this study, we first employed the OCO-2 data from 2020 to construct a Transformer-based structure and integrate prior constraint and hierarchical features injection mechanism for high precision CO₂ retrieval, and achieved an outstanding result with the R, RMSE, and MAPE of 0.939, 0.746 ppm, and 0.132 %. Based on the model, we evaluated its extrapolation capability using OCO-2 data from 2021 to 2024, demonstrating a robust performance and strong generalization ability (R = 0.938–0.951, RMSE = 1.083–1.310 ppm, MAPE = 0.208–0.256 %). Finally, we assessed the transferability of this model using simulated Tansat-2 data (August 18, 2020), achieving metrics of R = 0.657, RMSE = 1.299 ppm, and MAPE = 0.239 %, indicating the model’s effective transfer capabilities. The proposed model has the potential to provide a feasible solution for rapidly retrieving high-precision CO₂, especially for the next generation of large-swath carbon satellites.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"233 ","pages":"Pages 423-436"},"PeriodicalIF":12.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}