International journal of applied earth observation and geoinformation : ITC journal最新文献

{"title":"A new sparse reconstruction framework integrating parallel photography with laser-coplanar directional control for constrained underground spaces","authors":"Rongchun Zhang ,&nbsp;Jie Zhao ,&nbsp;Liang Cheng ,&nbsp;Xuefeng Yi ,&nbsp;Liang Ge ,&nbsp;Song Chen ,&nbsp;Dongchuan Wang ,&nbsp;Yi Jiang","doi":"10.1016/j.jag.2026.105149","DOIUrl":"10.1016/j.jag.2026.105149","url":null,"abstract":"<div><div>In the field of underground engineering, particularly in water conservancy, hydropower, and transportation tunnel projects, the high-resolution reconstruction of deep-buried long tunnels and other confined underground spaces serves as a fundamental data source for precise, efficient, and safe measurement of geological parameters. Due to the lack of control points and GNSS, important orientational data such as geological spatial attitude are difficult to be measured. Parallel photogrammetry can quickly acquire highly overlapping image data, but it still suffers from significant cumulative model drift and lack of absolute true geo-referenced pose in long tunnel reconstruction. To address these challenges, a novel sparse reconstruction method is proposed that integrates parallel photography with laser-coplanar directional control. First, an absolute orientation control system is established, in which the underground spaces with true directional geo-reference can be determined by combination of a geological compass and a laser level, i.e., a geological compass is used to measure absolute direction and a laser level is used to determine the vertical and horizontal pose angles parameters. Laser feature correspondences are extracted from both vertical and horizontal laser planars through a deep convolutional matching network guided by projected laser lines. These absolute orientation parameters, together with the global planar constraints, are incorporated as novel geometric constraints for the bundle adjustment optimization. The proposed method not only provides an absolute direction reference in constrained underground scenes without relying on GNSS, effectively mitigates model drift and enhances sparse reconstruction accuracy.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105149"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"First validation of the Lightning Imager aboard Meteosat Third Generation satellite with Earth Networks Total Lightning Network","authors":"Vojtěch Bližňák,&nbsp;Zbyněk Sokol","doi":"10.1016/j.jag.2026.105205","DOIUrl":"10.1016/j.jag.2026.105205","url":null,"abstract":"<div><div>The Meteosat Third Generation Lightning Imager (MTG-LI), launched aboard the MTG-Imager-1 satellite, is the first geostationary optical lightning sensor to cover Europe and Africa while also covering parts of South America. It enables continuous monitoring of total lightning (both intra-cloud (IC) and cloud-to-ground (CG)) with high temporal and spatial resolution. This study presents the first validation of LI observations over South America and adjacent regions during October 2024, using data from the ground-based Earth Networks Total Lightning Network (ENTLN). Three objectives are addressed: (i) evaluation of LI’s detection capabilities across varying spatiotemporal thresholds; (ii) assessment of the temporal accuracy of LI; and (iii) investigation of the empirical relationship between ENTLN peak current (A) and LI optical radiance (R). Our results show that in areas with dense ground network coverage, detection efficiency exceeds 0.8 and FAR is below 0.3 using moderate thresholds (±2 s, 1° x 1°). Relatively high FAR values, particularly at night, are in-part due to LI detecting lightning that ENTLN misses in areas where its performance is reduced. In addition, a regression model of the A–R relationship is proposed enabling the peak current to be estimated based solely on satellite data, which is advantageous in areas with insufficient ground-based observations. The results show that this relationship is more suitable in logarithmic transformation, with positive discharges exhibiting twice the regression slope than negative discharges.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105205"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147360594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-pass InSAR analysis of the estuarine alluvial Chongming Island ground displacements with implications on flood risk","authors":"Qing Zhao ,&nbsp;Lei Zhou ,&nbsp;Yifei Zhang ,&nbsp;Antonio Pepe ,&nbsp;Chengfang Yao ,&nbsp;Jingjing Wang ,&nbsp;Yuanzhi Yao","doi":"10.1016/j.jag.2025.105057","DOIUrl":"10.1016/j.jag.2025.105057","url":null,"abstract":"<div><div>Chongming Island of Shanghai, the largest estuarine alluvial island of China, has been kept seaward expanding due to continuous riverine sediment deposits and extensive land reclamation. Moreover, the island is highly vulnerable to long-term ground deformations and rising sea levels. To evaluate the influence of coastal ground deformation on flood risk, we investigated long-term ground deformation on Chongming Island over the last decade using RADARSAT-2 and Sentinel-1A satellite datasets collected from 2012 to 2023. The independently achieved ground deformation time series, representing the projection of ground displacement along the radar line of sight (LOS) direction (recovered using traditional multi-temporal interferometric SAR algorithms), were then jointly combined. The results show that the eastern region of Chongming Island has been experiencing significant ground subsidence over the last decade, with a maximum amplitude exceeding 20 mm/year. The significant ground subsidence in the eastern island occurred at a rate at least 2.5 times that of the concurrent sea level rise (SLR).</div><div>Furthermore, we analyzed the coastal flood risk on Chongming Island under the comprehensive effects of local ground subsidence, SLR, and storm surges. To this aim, a hydrodynamic model was applied to simulate various inundation scenarios on Chongming Island after failures of different seawall sections. As the major outcome of our work, under the simulated scenario (e.g., the worst case), the total flood inundation area in 2042 was estimated to exceed 50% of the island. Under this worst scenario, almost all of the salt marsh vegetation in Chongming Dongtan Nature Reserve would be flooded after the relative SLR. The loss of elevation in the low-lying island further aggravates the coastal flooding risk. Therefore, preserving the stability of eastern and northern seawalls is essential to the security of Chongming Island in the context of the increasing flooding risk in the low-lying river estuary.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105057"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Remote sensing for cultural heritage: A systematic review","authors":"Fulong Chen ,&nbsp;Peifeng Ma ,&nbsp;Siliang Chen ,&nbsp;Qingwu Hu ,&nbsp;Huadong Guo","doi":"10.1016/j.jag.2025.105039","DOIUrl":"10.1016/j.jag.2025.105039","url":null,"abstract":"<div><div>Cultural heritage is an integrated system that encompasses both heritage ontology and their surrounding environments. Traditional methods, such as field measurements, are often inefficient and fragmented in assessing the condition of cultural heritage. In recent years, remote sensing has emerged as a crucial tool for the systematic safeguarding and conservation of cultural heritage, thanks to its high spatiotemporal observation capabilities. Utilizing optical, radar, and laser sensors mounted on satellites, aircraft, unmanned aerial vehicles, and terrestrial platforms, remote sensing offers a comprehensive approach to ensure the sustainability of cultural heritage. This study addresses critical gaps in the emerging, interdisciplinary field of remote sensing for cultural heritage—including limited terrestrial platform coverage, underutilized AI paradigms, and insufficient policy integration—by conducting a systematic, state-of-the-art bibliometric analysis of peer-reviewed papers from the Web of Science Core Collection (1900–2024). Based on this analysis, we summarized the applicable methods, sensor platforms, and applications of remote sensing in cultural heritage conservation and proposed a theoretical framework incorporating relevant methodologies and models. Our results indicate that the integration of multi-spatiotemporal data and diverse technologies is a key characteristic of the disciplinary development. In addition, to application-oriented methodologies, hazard-risk mapping and sustainability assessment of cultural heritage are identified as two potential future directions, which align with the progress assessment of Sustainable Development Goal Target 11.4 by harnessing economic, political and institutional drivers in concert. Leveraging artificial intelligence, data-driven knowledge mining, and multi-source coupling, remote sensing for cultural heritage is transitioning from heritage-specific sustainability through systematic monitoring and evaluation to a broader focus on regional sustainability where heritage sites are located.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105039"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Geographically weighted regression model-assisted (GWRMA) estimation to improve precision of estimates combining remote sensing and ground plot data","authors":"Dingfan Xing ,&nbsp;Nicholas N. Nagle ,&nbsp;Stephen V. Stehman ,&nbsp;Todd A. Schroeder","doi":"10.1016/j.jag.2025.105045","DOIUrl":"10.1016/j.jag.2025.105045","url":null,"abstract":"<div><div>Remotely sensed data play a vital role providing auxiliary variables that can improve precision of sample-based estimates without incurring the substantial cost of increasing sample size. In the setting of design-based inference, model-assisted estimators using generalized regression models provide a practical option to exploit such auxiliary variables to obtain estimates with smaller uncertainties than the Horvitz-Thompson (HT) estimator. Spatial heterogeneity is one of the main characteristics of spatial geographical populations and spatial nonstationarity in regression model parameters can greatly impact model predictions. However, model-assisted estimators typically do not incorporate spatial heterogeneity in the assisting models, and this may result in failing to gain the full precision improvement available from model-assisted estimation. Geographically Weighted Regression (GWR) offers a practical way to incorporate spatial heterogeneity of the data into the model. In this study, we substantiate the benefit of employing a GWR model-assisted estimator (GWRMA) in which GWR is used as a linking model between the response and auxiliary variables. The illustrative example we use to demonstrate the precision enhancing capacity of GWRMA is estimating tree volume in forest inventory monitoring. The performance of GWRMA was compared with the HT estimator and a linear regression model-assisted (LRMA) estimator when both the response and auxiliary variables are continuous. Several factors potentially impacting the estimators and their precision were investigated using Monte-Carlo simulation applied to populations constructed to represent different levels of spatial heterogeneity and correlation between the response and auxiliary variables. Because both LRMA and GWRMA estimators are asymptotically unbiased, variance is the key criterion for comparing the estimators. For the constructed populations with spatial heterogeneity, the GWRMA estimator achieved standard errors smaller than the HT and LRMA estimators, and the improvement in precision increased with increasing sample size. The precision advantage of the GWRMA estimator relative to the LRMA estimator was attributable to the capacity of the GWRMA estimator to adapt to spatial variation in the regression model leading to better local prediction of the target variable. The conventional model-assisted variance estimator substantially underestimated the variance of the GWRMA estimator. An alternative variance estimator based on averaging the GWRMA and LRMA variance estimates avoided the severe underestimation of the conventional model-assisted variance estimator. This average variance estimator yielded confidence intervals that exceeded the nominal 90% coverage but still had shorter length than the 90 % confidence intervals from LRMA estimator. Further exploration of variance estimators for the GWRMA estimator is a necessary next step to improve utility of the GWRMA estimator.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105045"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simplifying the bipartite matching topology recovery for vectorized building footprint extraction","authors":"Libo Cheng ,&nbsp;Han Hu ,&nbsp;Liupeng Su ,&nbsp;Zeyuan Dai ,&nbsp;Lihua Zhang ,&nbsp;Guanyan Yang ,&nbsp;Bo Xu ,&nbsp;Qing Zhu","doi":"10.1016/j.jag.2025.105071","DOIUrl":"10.1016/j.jag.2025.105071","url":null,"abstract":"<div><div>Extracting vectorized building footprints from high-resolution imagery requires precise corner localization, robust boundary connectivity, and the generation of spatially ordered topological structures that faithfully encompasses the building area. These interdependent requirements make current approaches complex, which typically rely on cascaded architectures combining heterogeneous neural networks for feature extraction and topological recovering separately. This paper proposes ABCNet, a unified CNN architecture that simultaneously extracts instance-level areas, boundaries, and corners while robustly recovering ordered topological sequences for building footprints. Specifically, we augment a standard YOLO-based instance segmentation network with dual detection heads to generate per-building instance mask scores for areas, boundaries, and corners. The initial exterior contour is derived from the instance area mask. To refine the footprint geometry beyond smoothed contour approximations, we establish geometrically ordered corner connections through a bipartite matching matrix. Each entry in this square matrix encodes the interpolated boundary probability score between two corners indexed by its row and column. Ordered relationships are estimated using path-length differences relative to the initial contour, computed from parameterized distances of orthogonally projected points along the contour. The vertex sequence direction (clockwise/counterclockwise) is resolved via the triangle inequality criterion. Finally, the topological sequence is recovered through linear-sum-assignment optimization applied to the bipartite matching matrix, giving the vectorized building. Experimental evaluation on two vectorized building extraction benchmarks demonstrates that the proposed method, despite its architectural simplicity, surpasses state-of-the-art approaches by significant margins—achieving 8.6% and 2.5% higher AP (Average Precision) under in-distribution and out-of-distribution scenarios, respectively; with a 3% improvement on human-annotated out-of-distribution vectorization benchmarks. Visual comparisons further reveal the method’s robustness, maintaining coherent degradation patterns even when geometric primitives are misdetected under challenging imaging conditions. The simple architecture inherently preserves design flexibility, enabling future enhancements to area, boundary, and corner detection precision through dedicated module refinements.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105071"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The first large-footprint hyperspectral LiDAR model to attempt to reveal forest chlorophyll distribution heterogeneity from vertically layered spectral perspective utilizing 3D radiative transfer modeling","authors":"Jie Bai ,&nbsp;Huaguo Huang ,&nbsp;Binbin He ,&nbsp;Lingfei Ma ,&nbsp;Shuai Gao ,&nbsp;Shuaifeng Peng ,&nbsp;Xuebo Yang ,&nbsp;Yishuo Hao ,&nbsp;Yuanbiao Dong ,&nbsp;Kaiyi Bi ,&nbsp;Li Wang ,&nbsp;Shihua Li ,&nbsp;Zheng Niu","doi":"10.1016/j.jag.2025.105060","DOIUrl":"10.1016/j.jag.2025.105060","url":null,"abstract":"<div><div>Vertical structural and spectral heterogeneity are two key remote sensing characteristics of complex forests. To enable effective forest health management and provide early warnings of abnormal disturbance, monitoring forest biochemical content with a vertically layered spectral perspective is critically needed. However, commonly used remote sensing technique still have limited capacity to study the biochemical status of the middle and lower canopy layers. This study provides the first insight into the potential of the full-waveform large-footprint hyperspectral LiDAR (LFHSL) system for retrieving the vertical heterogeneity of forest chlorophyll using 3D radiative transfer modeling. In our newly constructed LFHSL model, virtual three-dimensional (3D) complex forest scenes, comprising trees, bushes, and grass, were defined with varying positions and biochemical content inputs. Hyperspectral waveforms within the large-footprint were then simulated for each combination of vegetation position and biochemical level. The concept of spectral index time profiles (SITP), referred to as spectral index variation along the laser path, were introduced and used to assess the vertical distribution of chlorophyll for the first time in forest scenes. The main findings of this study are as follows: (1) Full-waveform LFHSL owns great potential for retrieving vertical chlorophyll content across trees, bushes, and grass layers in complex forest ecosystems. (2) SITP is a novel and essential reference indicator that fully registers chlorophyll variations along the laser path. (3) Simulations with random positions and chlorophyll contents indicate that the peak points of SITP yield higher chlorophyll prediction accuracy in trees layer and grass layer (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>: 0.996 vs. 0.971, RMSE: 1.39 vs. 3.81 <span><math><mrow><mi>μ</mi><mi>g</mi><mspace></mspace><msup><mrow><mi>cm</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></math></span>) than that of bushes layer (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.801, RMSE of 9.97 <span><math><mrow><mi>μ</mi><mi>g</mi><mspace></mspace><msup><mrow><mi>cm</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></math></span>). (4) Compared to position patterns, LFHSL system is more sensitive to chlorophyll content sets. This study demonstrates that full-waveform LFHSL is a promising and surely reliable tool for acquiring and monitoring vertical vegetation health in complex forests. It not only provides significant guiding for the development of laser radar models but also holds promise for adoption in design of large-footprint multi-spectral or hyperspectral LiDAR.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105060"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Platform geodetic synergy of InSAR, UAV, optical, and HD-ERT constrains kinematic evolution of the Jungong landslide (Yellow River Basin)","authors":"Xiaoyu Liu ,&nbsp;Wu Zhu ,&nbsp;Yuxin Zhou ,&nbsp;Jiewei Zhan ,&nbsp;Zhanxi Wei ,&nbsp;Jing Wu ,&nbsp;Haixing Shang ,&nbsp;Chao Du","doi":"10.1016/j.jag.2025.105082","DOIUrl":"10.1016/j.jag.2025.105082","url":null,"abstract":"<div><div>Following the September 20, 2019 instability event, the Jungong landslide—a large-scale red-bed feature in the upper Yellow River Basin—has exhibited persistent creep, necessitating systematic kinematic analysis to constrain deformation drivers. In this context, we conducted a multidisciplinary approach integrating interferometric synthetic aperture radar (InSAR), unmanned aerial vehicle (UAV) surveys, optical satellite remote sensing, and high-density electrical resistivity tomography (HD-ERT) to investigate its kinematic evolution. Firstly, interferometric processing of SAR imagery from ALOS/PALSAR-1, ALOS/PALSAR-2 and Sentinel-1 systems (March 2007-August 2024) revealed continuous creeping with maximum deformation velocity reaching −129 mm/yr in descending Sentinel-1. Based on morphological and deformation characteristics, the slope was divided into four secondary zones. Through digital image correlation (DIC) of optical images, horizontal displacements exceeding 20 m induced by instability were detected at the front edge of Zone I. The three-dimensional (3D) deformation field was then inverted by combining multi-orbit InSAR observations and a topography-constrained model, revealing significant spatial heterogeneity of displacement characteristics. The maximum velocities in the eastward, northward, and vertical directions were −107, 53, and −71 mm/yr, respectively. Additionally, the internal structure along two profiles was detected using HD-ERT. Finally, a method combining Singular Spectrum Analysis (SSA) and wavelet transform was proposed to quantitatively analyze the temporal relationship between periodic displacements and rainfall. Different zones exhibited varying degrees of correlation with rainfall, with a time lag of approximately 45 days in Zone I. This multidisciplinary approach enhances our understanding of the kinematic behavior of the Jungong landslide, providing critical reference for future hazard assessment.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105082"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145919767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative models for SAR–optical image translation: A systematic review","authors":"Zhao Wang ,&nbsp;Zheng Zhang ,&nbsp;Xiaojun Shan ,&nbsp;Hong-an Wei ,&nbsp;Ping Tang","doi":"10.1016/j.jag.2025.105009","DOIUrl":"10.1016/j.jag.2025.105009","url":null,"abstract":"<div><div>Growing demands in sustainable development and resource management are driving increasing reliance on remote sensing-based Earth observation and image interpretation. In parallel, multimodal collaborative processing is attracting research attention. Synthetic aperture radar (SAR) and optical images offer complementary advantages but pose challenges for simultaneous use due to platform constraints and environmental conditions, often leaving only one modality available and impeding joint analysis. Generative models, particularly generative adversarial networks (GANs) and diffusion models (DMs), address this by learning cross-modal mappings. Translated images preserve structure and semantics while adopting target characteristics, thereby facilitating collaborative use. This review systematically categorizes translation frameworks spanning GANs, DMs, and other generative models. It then details downstream tasks supported by SAR–optical translation, including cloud removal, change detection, semantic segmentation, registration, and object detection, highlighting how translation bridges data gaps and enhances interpretation robustness. Furthermore, we provide open-source code and public datasets, discuss current challenges, and outline future research directions.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105009"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seeing through the noise: A cross-modal guided framework for hyperspectral image classification under multi-type degradations","authors":"Hui Liu ,&nbsp;Wei Tong ,&nbsp;Ning Chen ,&nbsp;Tao Xie ,&nbsp;Chenjia Huang ,&nbsp;Xia Yue ,&nbsp;Zhou Huang","doi":"10.1016/j.jag.2026.105117","DOIUrl":"10.1016/j.jag.2026.105117","url":null,"abstract":"<div><div>Recent advances in deep learning and multimodal data fusion technologies have significantly enhanced hyperspectral image (HSI) classification performance. Nevertheless, classification accuracy of hyperspectral data continues to degrade substantially under diverse degradation scenarios, such as noise interference, spectral distortion, or reduced resolution. To robustly address this challenge, this paper proposes a novel cross-modal guided classification framework that integrates active remote sensing data (e.g., LiDAR) to improve classification resilience under degraded conditions. Specifically, we introduce a Cross-Modal Feature Pyramid Guidance (CMFPG) module, which effectively utilizes cross-modal information across multiple levels and scales to guide hyperspectral feature extraction and fusion, thereby enhancing modeling stability in degraded environments. Additionally, we develop the HyperGroupMix module, which enhances cross-domain adaptability through grouping spectral bands, extracting statistical features, and transferring features across samples. Experimental results conducted under complex degradation conditions demonstrate that our proposed method exhibits stable high-level classification accuracy and robustness in overall performance. The code is accessible at: <span><span>https://github.com/miliwww/CMGF</span><svg><path></path></svg></span></div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"146 ","pages":"Article 105117"},"PeriodicalIF":8.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}