Boyun Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Boyun Yu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Takashi Oguchi
Center for Spatial Information Science, The University of Tokyo, Kashiwa, Japan
5 shared publications - Kotaro Iizuka
Center for Spatial Information Science, the University of Tokyo, Kashiwa 277-8568, Japan
4 shared publications Noé Delloye
2 shared publications- Alessandro Cesare Mondini
Institute of Hazard, Risk and Resilience, Durham University, Durham, UK
1 shared publication Alessandro Mercurio
1 shared publicationAlessandro Simoni
1 shared publication
Latest Publications
- Open Access
- 28 October 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 44
Inventories of multi-type landslides for deep learning- and remote sensing-based mapping: A case of the 2024 Noto Peninsula events, Japan
- 28 October 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 44
Open AccessInventories of multi-type landslides for deep learning- and remote sensing-based mapping: A case of the 2024 Noto Peninsula events, Japan
- Open Access
- 6 August 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (15) , 2619
An Interpretable Uncertainty-Aware Framework for Landslide Susceptibility Mapping Based on Weak Supervision and Probabilistic Inference
Landslide susceptibility mapping infers future slope-failure potential from observed landslides. This inference is uncertain because locations without recorded failures cannot be confirmed as stable or used as reliable negatives, and incomplete inventories, geomorphic complexity, spatial representation, sampling, and model dependence further increase uncertainty. To address these challenges, this study developed an interpretable, uncertainty-aware framework integrating joint SHAP–PFI feature assessment, weakly supervised negative-sample construction, and ensemble-based probabilistic inference. The framework yielded relative probabilistic susceptibility estimates, together with predictive uncertainty (), characterizing predictive ambiguity, and ensemble-based model uncertainty (), characterizing bootstrap variability. The framework was applied in northern Noto, Japan, using a legacy inventory and an independent 2024 event-based landslide inventory at the pixel and slope-unit scales and across seven model families. Joint SHAP–PFI analysis combined contribution magnitude and predictive dependence to support scale-specific factor selection. Ablation analyses showed that weak supervision improved independent-event generalization and reduced uncertainty. For LightGBM, independent-positive Recall increased from 0.76 to 0.83, decreased from 0.18 to 0.065, and from 0.019 to 0.0085. Ensemble learning quantified spatial uncertainty while maintaining independent-positive Recall comparable to both single-model controls. The framework was effective across tree-based, regression-based, and neural-network architectures, with LightGBM showing a stable cross-scale balance: independent-positive Recall was 0.83 and 0.77, and was 0.065 and 0.10 at the pixel and slope-unit scales, respectively. Spatial analysis further showed that uncertainty highlights areas where susceptibility estimates require caution. Overall, the framework quantifies and reduces uncertainty while improving independent-event generalization, thereby supporting more reliable landslide susceptibility assessment.- 6 August 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (15) , 2619
Open AccessAn Interpretable Uncertainty-Aware Framework for Landslide Susceptibility Mapping Based on Weak Supervision and Probabilistic Inference
Landslide susceptibility mapping infers future slope-failure potential from observed landslides. This inference is uncertain because locations without recorded failures cannot be confirmed as stable or used as reliable negatives, and incomplete inventories, geomorphic complexity, spatial representation, sampling, and model dependence further increase uncertainty. To address these challenges, this study developed an interpretable, uncertainty-aware framework integrating joint SHAP–PFI feature assessment, weakly supervised negative-sample construction, and ensemble-based probabilistic inference. The framework yielded relative probabilistic susceptibility estimates, together with predictive uncertainty (), characterizing predictive ambiguity, and ensemble-based model uncertainty (), characterizing bootstrap variability. The framework was applied in northern Noto, Japan, using a legacy inventory and an independent 2024 event-based landslide inventory at the pixel and slope-unit scales and across seven model families. Joint SHAP–PFI analysis combined contribution magnitude and predictive dependence to support scale-specific factor selection. Ablation analyses showed that weak supervision improved independent-event generalization and reduced uncertainty. For LightGBM, independent-positive Recall increased from 0.76 to 0.83, decreased from 0.18 to 0.065, and from 0.019 to 0.0085. Ensemble learning quantified spatial uncertainty while maintaining independent-positive Recall comparable to both single-model controls. The framework was effective across tree-based, regression-based, and neural-network architectures, with LightGBM showing a stable cross-scale balance: independent-positive Recall was 0.83 and 0.77, and was 0.065 and 0.10 at the pixel and slope-unit scales, respectively. Spatial analysis further showed that uncertainty highlights areas where susceptibility estimates require caution. Overall, the framework quantifies and reduces uncertainty while improving independent-event generalization, thereby supporting more reliable landslide susceptibility assessment. - Open Access
- 26 June 2026
- Published by California Digital Library (CDL) in EarthArXiv
Automated landslide detection in SAR wrapped interferograms using a geomorphology-constrained YOLO CNN
Slow-moving landslides pose significant hazards in mountain environments, requiring improved detection and monitoring capabilities. Traditional mapping is accurate but time-consuming, while multitemporal InSAR approaches are limited by data complexity and velocity constraints. Wrapped dual-pass DInSAR interferograms offer an alternative by preserving deformation signals without phase unwrapping, enabling detection across a wide range of movement rates. We present a deep learning framework for the automated detection and classification of active slow landslides in Sentinel-1 wrapped SAR interferograms. The model uses a YOLO convolutional neural network ingesting wrapped phase, an InSAR reliability index, and a terrain morphometric attribute layer. We trained, validated, and tested the network on 2243 labelled DInSAR wrapped phase signals from expert geomorphological interpretation over a 1200 km² sector of the Northern Apennines (Italy), using interferograms from ascending and descending orbits generated with multiple temporal baselines between 6 and 30 days. The network outputs bounding boxes with movement classification, achieving a mean Average Precision of 0.88 and an F1 score of 0.75. It successfully identifies deformation signals across multiple spatial scales, also in interferograms with low signal-to-noise ratio. Our results demonstrate the potential of wrapped DInSAR data combined with deep learning for efficient regional-scale landslide detection and inventory updating.
- 26 June 2026
- Published by California Digital Library (CDL) in EarthArXiv
Open AccessAutomated landslide detection in SAR wrapped interferograms using a geomorphology-constrained YOLO CNN
Slow-moving landslides pose significant hazards in mountain environments, requiring improved detection and monitoring capabilities. Traditional mapping is accurate but time-consuming, while multitemporal InSAR approaches are limited by data complexity and velocity constraints. Wrapped dual-pass DInSAR interferograms offer an alternative by preserving deformation signals without phase unwrapping, enabling detection across a wide range of movement rates. We present a deep learning framework for the automated detection and classification of active slow landslides in Sentinel-1 wrapped SAR interferograms. The model uses a YOLO convolutional neural network ingesting wrapped phase, an InSAR reliability index, and a terrain morphometric attribute layer. We trained, validated, and tested the network on 2243 labelled DInSAR wrapped phase signals from expert geomorphological interpretation over a 1200 km² sector of the Northern Apennines (Italy), using interferograms from ascending and descending orbits generated with multiple temporal baselines between 6 and 30 days. The network outputs bounding boxes with movement classification, achieving a mean Average Precision of 0.88 and an F1 score of 0.75. It successfully identifies deformation signals across multiple spatial scales, also in interferograms with low signal-to-noise ratio. Our results demonstrate the potential of wrapped DInSAR data combined with deep learning for efficient regional-scale landslide detection and inventory updating.
- Open Access
- 14 March 2026
- Published by Copernicus GmbH
The Eye of Disaster: Development and Evaluation of a VR-Based Landslide Education System
This study develops an immersive Virtual Reality (VR) pedagogical framework to mitigate the spatial cognitive constraints inherent in conventional two-dimensional disaster-prevention education. It focuses on the 2024 Noto Peninsula landslide events in Japan. By integrating high-precision digital elevation models and satellite imagery, the produced system reconstructs post-disaster terrains to facilitate high-fidelity risk communication. The interaction logic, governed by the natural user interface principles, incorporates a multi-perspective switching mechanism that enables users to conduct comprehensive analyses of disaster sites across varying spatial scales. The system architecture comprises two core modules: the "VR Geological Museum" for knowledge acquisition and the "Evacuation Simulation" for practical application, enabling deep transfer from conceptual understanding to survival skills. The former employs a task-driven strategy and a "macro-micro" dual-perspective observation model. It transforms abstract geological knowledge into intuitive interactive experiences through high-precision 3D reconstructions of landslide topography, effectively lowering the cognitive threshold for non-expert learners. Complementing this, the evacuation simulation module integrates official landslide-disaster warning area maps from the Geospatial Information Authority of Japan. Grounded in embodied cognition theory, this module implements a "trial-and-error" feedback mechanism. By navigating highly restored disaster evolution scenarios, users translate static warning information into dynamic survival capabilities, thereby completing the cognitive loop from theoretical understanding to behavioral practice. The pedagogical efficacy of the system was empirically validated through a randomized controlled trial, utilizing multidimensional standardized metrics, including the Presence Questionnaire, the System Usability Scale, and the NASA Task Load Index for workload assessment. Experimental results demonstrate that the system significantly outperforms traditional text-based media in knowledge internalization, risk perception accuracy, and survival decision-making efficiency. The core contribution of this research lies in the deep integration of high-fidelity geospatial data with immersive interaction, establishing a verifiable technical paradigm for disaster education. This approach effectively dismantles barriers to professional knowledge. It enhances disaster preparedness and evacuation efficacy across diverse demographic backgrounds, providing a robust theoretical and technical foundation for the universalization of geohazard education.
- 14 March 2026
- Published by Copernicus GmbH
Open AccessThe Eye of Disaster: Development and Evaluation of a VR-Based Landslide Education System
This study develops an immersive Virtual Reality (VR) pedagogical framework to mitigate the spatial cognitive constraints inherent in conventional two-dimensional disaster-prevention education. It focuses on the 2024 Noto Peninsula landslide events in Japan. By integrating high-precision digital elevation models and satellite imagery, the produced system reconstructs post-disaster terrains to facilitate high-fidelity risk communication. The interaction logic, governed by the natural user interface principles, incorporates a multi-perspective switching mechanism that enables users to conduct comprehensive analyses of disaster sites across varying spatial scales. The system architecture comprises two core modules: the "VR Geological Museum" for knowledge acquisition and the "Evacuation Simulation" for practical application, enabling deep transfer from conceptual understanding to survival skills. The former employs a task-driven strategy and a "macro-micro" dual-perspective observation model. It transforms abstract geological knowledge into intuitive interactive experiences through high-precision 3D reconstructions of landslide topography, effectively lowering the cognitive threshold for non-expert learners. Complementing this, the evacuation simulation module integrates official landslide-disaster warning area maps from the Geospatial Information Authority of Japan. Grounded in embodied cognition theory, this module implements a "trial-and-error" feedback mechanism. By navigating highly restored disaster evolution scenarios, users translate static warning information into dynamic survival capabilities, thereby completing the cognitive loop from theoretical understanding to behavioral practice. The pedagogical efficacy of the system was empirically validated through a randomized controlled trial, utilizing multidimensional standardized metrics, including the Presence Questionnaire, the System Usability Scale, and the NASA Task Load Index for workload assessment. Experimental results demonstrate that the system significantly outperforms traditional text-based media in knowledge internalization, risk perception accuracy, and survival decision-making efficiency. The core contribution of this research lies in the deep integration of high-fidelity geospatial data with immersive interaction, establishing a verifiable technical paradigm for disaster education. This approach effectively dismantles barriers to professional knowledge. It enhances disaster preparedness and evacuation efficacy across diverse demographic backgrounds, providing a robust theoretical and technical foundation for the universalization of geohazard education.
- Open Access
- 13 March 2026
- Published by Copernicus GmbH
Construction and Quality Evaluation of AI-based Landslide Inventory Maps for the 2024 Noto Peninsula Events, Japan
Under a changing climate, landslides pose significant risks to human society and regional sustainability. Advances in remote sensing and Artificial Intelligence (AI) have enabled automated large-scale landslide mapping after events. However, most existing AI-based inventories treat landslides as a single class, overlooking typological differentiation and providing limited assessment of geographic accuracy, which are central concerns in Landslide Inventory Maps (LIMs) research. This oversight obscures geomorphological diversity and spatial heterogeneity, constraining their use in geomorphological investigations and analyses beyond simple detection. As a result, the lack of explicit evaluation of thematic and geographic accuracy in AI-based landslide inventories remains an unresolved scientific problem.To bridge this gap, this study developed and evaluated AI-based multi-class landslide inventories derived from PlanetScope and SPOT-6 imagery in the northern Noto Peninsula, Japan, and validated them through two-point field surveys (Figure 1). The study area (37.40°–37.49°N, 137.01°–137.19°E) lies along the Sea of Japan coast of central Honshu, at the convergent boundary between the Okhotsk and Amurian plates, where active reverse faults have been repeatedly reactivated. In 2024, the area was affected by two major landslide-triggering events: an Mw 7.6 earthquake on 1st January and an episode of extreme rainfall in September. These events generated widespread but contrasting slope failures and were used to construct two post-event LIMs.Results indicate that the inventories consistently identify three failure types, falls, slides, and flows, with 1,677 landslides mapped after the earthquake and 2,511 after the rainfall. Landslide areas follow log-normal size distributions, with slides covering the largest total area and flows exhibiting the highest counts. Compared with the earthquake, rainfall triggered more numerous but generally smaller failures.We further evaluated the thematic and geographic accuracy of the constructed LIMs against established geomorphological understanding. Falls preferentially occur near active faults and on conglomerates, where rock masses are mechanically weakened. Flows predominantly concentrate in natural valleys and headwater channels, and are associated with porous volcanic-ash deposits, favoring material mobilization. Slides mainly develop on sandstone–mudstone interbeds, reflecting contrasting mechanical properties along bedding planes. Slope is the strongest control, especially for falls and flows, with failures concentrated on steep slopes characterized by concave curvature and steep longitudinal profiles. These geomorphologically consistent patterns support both thematic and geographic accuracy.Finally, suitability for AI applications was assessed using thirteen semantic segmentation models. DRANet and TransUNet achieved the highest accuracy (mIoU > 0.85), providing precise landslide boundaries suitable for geomorphological analysis and modeling. In contrast, SwinUNet and SegFormer offer efficient trade-offs (around 0.80 mIoU with
- 13 March 2026
- Published by Copernicus GmbH
Open AccessConstruction and Quality Evaluation of AI-based Landslide Inventory Maps for the 2024 Noto Peninsula Events, Japan
Under a changing climate, landslides pose significant risks to human society and regional sustainability. Advances in remote sensing and Artificial Intelligence (AI) have enabled automated large-scale landslide mapping after events. However, most existing AI-based inventories treat landslides as a single class, overlooking typological differentiation and providing limited assessment of geographic accuracy, which are central concerns in Landslide Inventory Maps (LIMs) research. This oversight obscures geomorphological diversity and spatial heterogeneity, constraining their use in geomorphological investigations and analyses beyond simple detection. As a result, the lack of explicit evaluation of thematic and geographic accuracy in AI-based landslide inventories remains an unresolved scientific problem.To bridge this gap, this study developed and evaluated AI-based multi-class landslide inventories derived from PlanetScope and SPOT-6 imagery in the northern Noto Peninsula, Japan, and validated them through two-point field surveys (Figure 1). The study area (37.40°–37.49°N, 137.01°–137.19°E) lies along the Sea of Japan coast of central Honshu, at the convergent boundary between the Okhotsk and Amurian plates, where active reverse faults have been repeatedly reactivated. In 2024, the area was affected by two major landslide-triggering events: an Mw 7.6 earthquake on 1st January and an episode of extreme rainfall in September. These events generated widespread but contrasting slope failures and were used to construct two post-event LIMs.Results indicate that the inventories consistently identify three failure types, falls, slides, and flows, with 1,677 landslides mapped after the earthquake and 2,511 after the rainfall. Landslide areas follow log-normal size distributions, with slides covering the largest total area and flows exhibiting the highest counts. Compared with the earthquake, rainfall triggered more numerous but generally smaller failures.We further evaluated the thematic and geographic accuracy of the constructed LIMs against established geomorphological understanding. Falls preferentially occur near active faults and on conglomerates, where rock masses are mechanically weakened. Flows predominantly concentrate in natural valleys and headwater channels, and are associated with porous volcanic-ash deposits, favoring material mobilization. Slides mainly develop on sandstone–mudstone interbeds, reflecting contrasting mechanical properties along bedding planes. Slope is the strongest control, especially for falls and flows, with failures concentrated on steep slopes characterized by concave curvature and steep longitudinal profiles. These geomorphologically consistent patterns support both thematic and geographic accuracy.Finally, suitability for AI applications was assessed using thirteen semantic segmentation models. DRANet and TransUNet achieved the highest accuracy (mIoU > 0.85), providing precise landslide boundaries suitable for geomorphological analysis and modeling. In contrast, SwinUNet and SegFormer offer efficient trade-offs (around 0.80 mIoU with
- Open Access
- 20 February 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 41
Low-light enhancement on nighttime unmanned aerial vehicle (UAV) imagery for surveying vacant houses
- 20 February 2026
- Published by Elsevier in Remote Sensing Applications: Society and Environment
- Vol. 41
Open AccessLow-light enhancement on nighttime unmanned aerial vehicle (UAV) imagery for surveying vacant houses
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Development and Validation of the Japan High-Resolution Landslide Dataset (JHRLD): Integrating Remote Sensing and Deep Learning
Landslides are geomorphological hazards triggered by natural factors such as rainfall, seismic activity, and snowmelt. A landslide inventory is essential for understanding and assessing the processes, distribution, and risks associated with these events. While traditional manual mapping from aerial imagery delivers high accuracy for slope-scale studies, it is labor-intensive and impractical for large-scale applications. Advances in remote sensing technologies, including high-resolution satellite imagery and synthetic aperture radar (SAR), have significantly enhanced the efficiency of landslide detection over broader geographical scales. Concurrently, deep learning techniques, such as convolutional neural networks (CNNs), have revolutionized the field by automating landslide feature extraction and segmentation through remote sensing imagery, addressing the inefficiencies of manual methods.Current challenges include the regional distribution bias in remote sensing-based landslide datasets, with limited high-quality data available for regions like Japan. Additionally, the lack of systematic evaluation of optimal features and deep learning architectures hinders improvements in detection accuracy and model transferability.To address these gaps, we developed and validated the Japan High-Resolution Landslide Dataset (JHRLD), which integrates multi-sensor data encompassing spectral, SAR, and topographic features. The dataset comprises two subsets: Sentinel-2 for moderate-resolution (10 m) and PlanetScope for high-resolution (3 m) imagery, named after the optical images used for landslide delineation. Both subsets were designed based on a pool of 21 candidate features, including spectral bands, vegetation indices, SAR-derived backscatter metrics from Sentinel-1, and topographic attributes derived from the DEM published by the Geospatial Information Authority of Japan. A rigorous feature selection includes statistical and model-based evaluations, narrowing the list to the most significant features for landslide mapping, including green, red, NDVI, slope, and intensity.Three deep learning models were employed on the JHRLD: UNet++, DeepLabv3+, and Medical Transformer (MedT). These models were evaluated using the F1 score for evaluating the JHRLD’s robustness and reliability. Performance analysis revealed that each model exhibited unique strengths depending on dataset resolution. On the moderate-resolution Sentinel-2 dataset, UNet++ excelled in detecting smaller-scale landslides, achieving an F1 score of 0.70. In contrast, DeepLabv3+ performed best on the high-resolution PlanetScope dataset, achieving an F1 score of 0.69 and effectively capturing large-scale and complex features. MedT showcased its superiority in boundary delineation, achieving the F1 score of 0.70 and excelling in identifying intricate landslide features. These results affirm the JHRLD’s robustness and reliability, providing a strong foundation for high-precision landslide detection across diverse resolutions and environments.The JHRLD was validated in the Noto Peninsula, a region impacted by an Mw 7.5 earthquake and torrential rainfall in 2024. The model trained on the JHRLD demonstrated strong transferability, achieving an F1 score of 0.65 and a detection rate of 81% on this unseen area. Temporal and spatial analyses confirmed the JHRLD’s robustness, aligning well with observed hazard patterns under varying triggers.The findings highlight the JHRLD’s adaptability as a benchmark dataset and its social utility in disaster prevention planning and emergency response. Figure. Workflow for the JHRLD development and validation.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessDevelopment and Validation of the Japan High-Resolution Landslide Dataset (JHRLD): Integrating Remote Sensing and Deep Learning
Landslides are geomorphological hazards triggered by natural factors such as rainfall, seismic activity, and snowmelt. A landslide inventory is essential for understanding and assessing the processes, distribution, and risks associated with these events. While traditional manual mapping from aerial imagery delivers high accuracy for slope-scale studies, it is labor-intensive and impractical for large-scale applications. Advances in remote sensing technologies, including high-resolution satellite imagery and synthetic aperture radar (SAR), have significantly enhanced the efficiency of landslide detection over broader geographical scales. Concurrently, deep learning techniques, such as convolutional neural networks (CNNs), have revolutionized the field by automating landslide feature extraction and segmentation through remote sensing imagery, addressing the inefficiencies of manual methods.Current challenges include the regional distribution bias in remote sensing-based landslide datasets, with limited high-quality data available for regions like Japan. Additionally, the lack of systematic evaluation of optimal features and deep learning architectures hinders improvements in detection accuracy and model transferability.To address these gaps, we developed and validated the Japan High-Resolution Landslide Dataset (JHRLD), which integrates multi-sensor data encompassing spectral, SAR, and topographic features. The dataset comprises two subsets: Sentinel-2 for moderate-resolution (10 m) and PlanetScope for high-resolution (3 m) imagery, named after the optical images used for landslide delineation. Both subsets were designed based on a pool of 21 candidate features, including spectral bands, vegetation indices, SAR-derived backscatter metrics from Sentinel-1, and topographic attributes derived from the DEM published by the Geospatial Information Authority of Japan. A rigorous feature selection includes statistical and model-based evaluations, narrowing the list to the most significant features for landslide mapping, including green, red, NDVI, slope, and intensity.Three deep learning models were employed on the JHRLD: UNet++, DeepLabv3+, and Medical Transformer (MedT). These models were evaluated using the F1 score for evaluating the JHRLD’s robustness and reliability. Performance analysis revealed that each model exhibited unique strengths depending on dataset resolution. On the moderate-resolution Sentinel-2 dataset, UNet++ excelled in detecting smaller-scale landslides, achieving an F1 score of 0.70. In contrast, DeepLabv3+ performed best on the high-resolution PlanetScope dataset, achieving an F1 score of 0.69 and effectively capturing large-scale and complex features. MedT showcased its superiority in boundary delineation, achieving the F1 score of 0.70 and excelling in identifying intricate landslide features. These results affirm the JHRLD’s robustness and reliability, providing a strong foundation for high-precision landslide detection across diverse resolutions and environments.The JHRLD was validated in the Noto Peninsula, a region impacted by an Mw 7.5 earthquake and torrential rainfall in 2024. The model trained on the JHRLD demonstrated strong transferability, achieving an F1 score of 0.65 and a detection rate of 81% on this unseen area. Temporal and spatial analyses confirmed the JHRLD’s robustness, aligning well with observed hazard patterns under varying triggers.The findings highlight the JHRLD’s adaptability as a benchmark dataset and its social utility in disaster prevention planning and emergency response. Figure. Workflow for the JHRLD development and validation.