Xiangtao Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiangtao Fan has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Dianrun Zhao
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences
1 shared publication - Hongdeng Jian
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Jian Liu
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication Jianhao Xu
1 shared publicationLiangyun Liu
International Research Center of Big Data for Sustainable Development Goals
1 shared publication- Liangyun Liu
School of Remote Sensing, Beijing Normal University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 17 July 2026
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 63 (1)
Improving GOME-2C red solar-induced chlorophyll fluorescence retrieval by denoising on radiance spectra
1 Solar-induced chlorophyll fluorescence (SIF) is an optical signal emitted by vegetation during photosynthesis and provides a direct proxy for photosynthetic activity and physiological status. In ...
- 17 July 2026
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 63 (1)
Open AccessImproving GOME-2C red solar-induced chlorophyll fluorescence retrieval by denoising on radiance spectra
1 Solar-induced chlorophyll fluorescence (SIF) is an optical signal emitted by vegetation during photosynthesis and provides a direct proxy for photosynthetic activity and physiological status. In ...
- Open Access
- 15 July 2026
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 63 (1)
Understanding sensitivity and accuracy of time-series change detection algorithm across multiple land disturbance scenarios
1. Land disturbance, referring to various abrupt events distinct from natural succession processes (Stahl et al. 2023; Zhu et al. 2020), as well as ground deformations such as slow-moving landslide...
- 15 July 2026
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 63 (1)
Open AccessUnderstanding sensitivity and accuracy of time-series change detection algorithm across multiple land disturbance scenarios
1. Land disturbance, referring to various abrupt events distinct from natural succession processes (Stahl et al. 2023; Zhu et al. 2020), as well as ground deformations such as slow-moving landslide...
- Open Access
- 1 June 2026
- Published by Elsevier in SSRN Electronic Journal
End-to-End Monocular Building Height Estimation with Semantic Interval Guidance and Region-Aware Modulation
Accurate height estimation from single high-resolution satellite imagery remains a fundamental yet challenging problem in urban remote sensing. The primary difficulties stem from three aspects: insufficient cross-scale perception leads to blurred building boundaries; limited association between height interval modeling and global height semantics results in incomplete recovery of rooftop structural details; and uniform spatial modulation causes predictions in extreme-height regions to converge toward the mean, degrading local accuracy. To address these challenges, this paper proposes a novel monocular height estimation framework built upon a height-binned modeling paradigm and progressively optimized from global feature encoding to local spatial refinement. Specifically, a bidirectional multi-scale feature aggregation mechanism enhances cross-scale spatial perception; a semantic-guided height interval modeling module incorporates global height semantics into bin representations for more discriminative interval prediction; and a region-aware pixel-level modulation mechanism explicitly models height interval-spatial region relationships to suppress extreme-height prediction bias. Extensive experiments on DFC2023 and US3D benchmark datasets demonstrate consistently superior performance over all compared methods. Validation on GF-7 domestic satellite imagery further confirms the framework's generalization to distinct radiometric and imaging characteristics, demonstrating its practical value for large-scale domestic 3D urban mapping.
- 1 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessEnd-to-End Monocular Building Height Estimation with Semantic Interval Guidance and Region-Aware Modulation
Accurate height estimation from single high-resolution satellite imagery remains a fundamental yet challenging problem in urban remote sensing. The primary difficulties stem from three aspects: insufficient cross-scale perception leads to blurred building boundaries; limited association between height interval modeling and global height semantics results in incomplete recovery of rooftop structural details; and uniform spatial modulation causes predictions in extreme-height regions to converge toward the mean, degrading local accuracy. To address these challenges, this paper proposes a novel monocular height estimation framework built upon a height-binned modeling paradigm and progressively optimized from global feature encoding to local spatial refinement. Specifically, a bidirectional multi-scale feature aggregation mechanism enhances cross-scale spatial perception; a semantic-guided height interval modeling module incorporates global height semantics into bin representations for more discriminative interval prediction; and a region-aware pixel-level modulation mechanism explicitly models height interval-spatial region relationships to suppress extreme-height prediction bias. Extensive experiments on DFC2023 and US3D benchmark datasets demonstrate consistently superior performance over all compared methods. Validation on GF-7 domestic satellite imagery further confirms the framework's generalization to distinct radiometric and imaging characteristics, demonstrating its practical value for large-scale domestic 3D urban mapping.
- Open Access
- 27 March 2026
- Published by Elsevier in SSRN Electronic Journal
Modeling the development of the First Bend of the Yangtze River and its implications for fluvial reorganization
The First Bend of the Yangtze River is a geomorphologically significant feature whose origin has long been debated, largely owing to the lack of direct sedimentary constraints. Resolving its formation is therefore critical for reconstructing the broader evolutionary history of the Yangtze River system. In this study, we employ a numerical landscape evolution model that incorporates localized, spatially heterogeneous, and regionally intermittent tectonic uplift driven by the ongoing India–Eurasia collision. Guided by existing hypotheses and geological interpretations, our model simulates long-term landform evolution and drainage network reorganization in the First Bend region. The numerical results quantitatively demonstrate the dynamic processes shaping this iconic feature. Specifically, the pronounced surface uplift of the Laojun Mountain plays a fundamental role in triggering river capture and flow reversal, precipitating substantial drainage reorganization. The resulting sharp discontinuities in chi values reflect a profoundly disequilibrated fluvial system, which ultimately forged the distinctive drainage configuration of the First Bend. Furthermore, comparative analyses of chi-transformed longitudinal profiles for trunk rivers and their major tributaries reveal a strong coupling between profile transient states and tectonic forcing. Our findings indicate that spatially heterogeneous uplift tends to increase dispersion in chi-transformed profiles, whereas spatially uniform but rapid uplift is more likely to drive additional drainage area loss. Despite several simplifying assumptions, the numerical model effectively captures the essential geomorphic characteristics of the First Bend of the Yangtze River, with results that agree well with those derived from the natural drainage network. The simulations, together with integrated analyses, provide new insights into the Cenozoic evolution of the First Bend and further corroborate interpretations that its formation occurred during the late Oligocene to early Miocene in response to tectonic elevation of the Jianchuan Basin. More broadly, by incorporating realistic kinematic scenarios under robust geological constraints, this study advances a physically based modeling framework for elucidating the long-term geomorphic and tectonic evolution of the Yangtze River system.
- 27 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessModeling the development of the First Bend of the Yangtze River and its implications for fluvial reorganization
The First Bend of the Yangtze River is a geomorphologically significant feature whose origin has long been debated, largely owing to the lack of direct sedimentary constraints. Resolving its formation is therefore critical for reconstructing the broader evolutionary history of the Yangtze River system. In this study, we employ a numerical landscape evolution model that incorporates localized, spatially heterogeneous, and regionally intermittent tectonic uplift driven by the ongoing India–Eurasia collision. Guided by existing hypotheses and geological interpretations, our model simulates long-term landform evolution and drainage network reorganization in the First Bend region. The numerical results quantitatively demonstrate the dynamic processes shaping this iconic feature. Specifically, the pronounced surface uplift of the Laojun Mountain plays a fundamental role in triggering river capture and flow reversal, precipitating substantial drainage reorganization. The resulting sharp discontinuities in chi values reflect a profoundly disequilibrated fluvial system, which ultimately forged the distinctive drainage configuration of the First Bend. Furthermore, comparative analyses of chi-transformed longitudinal profiles for trunk rivers and their major tributaries reveal a strong coupling between profile transient states and tectonic forcing. Our findings indicate that spatially heterogeneous uplift tends to increase dispersion in chi-transformed profiles, whereas spatially uniform but rapid uplift is more likely to drive additional drainage area loss. Despite several simplifying assumptions, the numerical model effectively captures the essential geomorphic characteristics of the First Bend of the Yangtze River, with results that agree well with those derived from the natural drainage network. The simulations, together with integrated analyses, provide new insights into the Cenozoic evolution of the First Bend and further corroborate interpretations that its formation occurred during the late Oligocene to early Miocene in response to tectonic elevation of the Jianchuan Basin. More broadly, by incorporating realistic kinematic scenarios under robust geological constraints, this study advances a physically based modeling framework for elucidating the long-term geomorphic and tectonic evolution of the Yangtze River system.