中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地质与地球物理研究所
  3. 中国科学院地质与地球物理研究所
  4. 中国科学院页岩气与地质工程重点实验室
A progressive framework combining unsupervised and optimized supervised learning for debris flow susceptibility assessment

文献类型：期刊论文

作者Liu, Yongqiang3; Chen, Jianping3; Sun, Xiaohui1; Li, Yongchao2; Zhang, Yiwei3; Xu, Wanglai3; Yan, Jianhua3; Ji, Yaopeng3; Wang, Qing3
刊名CATENA
出版日期2024
卷号234页码:16
关键词Debris flow susceptibility Watershed unit Unsupervised learning Supervised learning Multi-source data
ISSN号0341-8162
DOI10.1016/j.catena.2023.107560
英文摘要This research aims to improve the reliability of debris flow susceptibility (DFS) assessment, which is crucial for disaster prevention and mitigation in mountainous regions. A progressive framework was proposed and applied to Pinggu District, Beijing, China. First, 16 debris flow predisposing factors (DFPFs) were selected, and the slope structure and soil stability were incorporated to account for material sources. Watershed units instead of grid units were used to extract data. Then, the multi-collinearity among the factors was reduced by using variance inflation factors (VIF) and information gain (IG), and 13 DFPFs were retained. Three unsupervised learning algorithms (i.e., affinity propagation (AP), Gaussian mixture model (GMM) and self-organizing maps (SOM)) were used to optimize the sampling strategy of non-debris flow units. Subsequently, the occurrence probability of debris flows in each unit was predicted by using four supervised learning algorithms (i.e., logistic regression (LR), random forest (RF), adaptive boosting (ADAB) and extreme gradient boosting (XGB)). They were optimized by a state-of-the-art meta-modeling approach. Finally, the DFPF's importance was ranked. The main contributions of our framework are establishing a high-quality data set and optimizing the prediction algorithms. The results show that the tree-based models perform well, and the boosting-based algorithms outperform the bagging-based algorithms. Supervised learning is more suitable for DFS assessment than unsupervised learning. Debris flows are most likely to occur on a dolomite consequent or diagonal slope with a relief amplitude above 540 m.
WOS关键词LANDSLIDE CONDITIONING FACTORS ; RANDOM FOREST ; LOGISTIC-REGRESSION ; MODEL ; PREDICTION ; CLASSIFICATION ; INITIATION ; ALGORITHM ; DISASTER ; HAZARDS
资助项目National Natural Science Foundation of China[41941017] ; National Natural Science Foundation of China[U1702241]
WOS研究方向Geology ; Agriculture ; Water Resources
语种英语
WOS记录号WOS:001092896500001
出版者ELSEVIER
资助机构National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China
源URL[http://ir.iggcas.ac.cn/handle/132A11/110680]  
专题地质与地球物理研究所_中国科学院页岩气与地质工程重点实验室
通讯作者Wang, Qing
作者单位1.Taiyuan Univ Technol, Epartment Earth Sci & Engn, Taiyuan 030024, Peoples R China
2.Chinese Acad Sci, Key Lab Shale Gas & Geoengn, Inst Geol & Geophys, Beijing 100029, Peoples R China
3.Jilin Univ, Coll Construct Engn, Changchun 130026, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Yongqiang,Chen, Jianping,Sun, Xiaohui,et al. A progressive framework combining unsupervised and optimized supervised learning for debris flow susceptibility assessment[J]. CATENA,2024,234:16.
APA Liu, Yongqiang.,Chen, Jianping.,Sun, Xiaohui.,Li, Yongchao.,Zhang, Yiwei.,...&Wang, Qing.(2024).A progressive framework combining unsupervised and optimized supervised learning for debris flow susceptibility assessment.CATENA,234,16.
MLA Liu, Yongqiang,et al."A progressive framework combining unsupervised and optimized supervised learning for debris flow susceptibility assessment".CATENA 234(2024):16.

入库方式： OAI收割

来源：地质与地球物理研究所

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。