Landslide spatial prediction distinguishing spatial constraints and temporal trends
文献类型：期刊论文
| 作者 | Zhao, Zheng1,3,4; Lan, Hengxing2,3; Ouyang, Chaojun1,4; Li, Langping1,3; Zhao, Guanhua1,3; Liu, Jie1,3 |
| 刊名 | ENGINEERING GEOLOGY
 |
| 出版日期 | 2026-05-21 |
| 卷号 | 367页码:108703 |
| 关键词 | Landslides Deep learning Spatiotemporal prediction Surface deformation InSAR |
| ISSN号 | 0013-7952 |
| DOI | 10.1016/j.enggeo.2026.108703 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Landslide spatial prediction is often hindered by conventional models that conflate long-term predisposing factors with short-term triggering signals, limiting their ability to capture, disentangle, and integrate spatiotemporal information. To address this limitation, we propose a new method that explicitly distinguishes spatial constraints and temporal trends. Specifically, a graph neural network guided by the Third Law of Geography is used to learn representations from stable spatial features, while a temporal Transformer encodes the timevarying dynamics of surface deformation. The resulting spatial and temporal embeddings are then fused to enable effective cross-modal information aggregation. We implement and validate the proposed framework in Luding County and the upper Jinsha River region. Results show that, across three mapping units, our method consistently outperforms representative machine-learning baselines (e.g., spatial-only and temporal-only strategies), yielding the improvements of 8.7%, 13.0%, and 8.3% in the area under the receiver operating characteristics curve, respectively. Moreover, slope units provide better predictive performance than grid and triangular irregular network (TIN) units for landslide susceptibility modelling. To our knowledge, this is the first approach to explicitly model spatial and temporal characteristics as heterogeneous inputs, treating long-term predisposing factors and InSAR-derived deformation sequences as distinct modalities, thereby addressing a key challenge in multi-modal feature extraction. These findings suggest that the proposed framework offers a promising solution for landslide spatial prediction and could support operational early warning when integrated with external triggering indicators. |
| URL标识 | 查看原文 |
| WOS研究方向 | Engineering ; Geology |
| 语种 | 英语 |
| WOS记录号 | WOS:001727819000001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221524]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Lan, Hengxing; Ouyang, Chaojun |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Changan Univ, Sch Geol Engn & Geomat, Xian 710064, Peoples R China; 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China; 4.Chinese Acad Sci, Inst Mt Hazards & Environm, Key Lab Mt Hazards & Engn Resilience, Chengdu 610299, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zhao, Zheng,Lan, Hengxing,Ouyang, Chaojun,et al. Landslide spatial prediction distinguishing spatial constraints and temporal trends[J]. ENGINEERING GEOLOGY,2026,367:108703. |
| APA | Zhao, Zheng,Lan, Hengxing,Ouyang, Chaojun,Li, Langping,Zhao, Guanhua,&Liu, Jie.(2026).Landslide spatial prediction distinguishing spatial constraints and temporal trends.ENGINEERING GEOLOGY,367,108703. |
| MLA | Zhao, Zheng,et al."Landslide spatial prediction distinguishing spatial constraints and temporal trends".ENGINEERING GEOLOGY 367(2026):108703. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。