On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values
文献类型：期刊论文
| 作者 | Wang, Nan9; Zhang, Hongyan; Dahal, Ashok8; Cheng, Weiming5,6,7,9; Zhao, Min2,3,4; Lombardo, Luigi8 |
| 刊名 | GEOSCIENCE FRONTIERS
 |
| 出版日期 | 2024-07-01 |
| 卷号 | 15期号:4页码:101800 |
| 关键词 | Hydro-morphological processes SHAP maps Explainable AI China |
| DOI | 10.1016/j.gsf.2024.101800 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Hydro-morphological processes (HMP, any natural phenomenon contained within the spectrum defined between debris flows and flash floods) are globally occurring natural hazards which pose great threats to our society, leading to fatalities and economical losses. For this reason, understanding the dynamics behind HMPs is needed to aid in hazard and risk assessment. In this work, we take advantage of an explainable deep learning model to extract global and local interpretations of the HMP occurrences across the whole Chinese territory. We use a deep neural network architecture and interpret the model results through the spatial pattern of SHAP values. In doing so, we can understand the model prediction on a hierarchical basis, looking at how the predictor set controls the overall susceptibility as well as doing the same at the level of the single mapping unit. Our model accurately predicts HMP occurrences with AUC values measured in a ten-fold cross-validation ranging between 0.83 and 0.86. This level of predictive performance attests for an excellent prediction skill. The main difference with respect to traditional statistical tools is that the latter usually lead to a clear interpretation at the expense of high performance, which is otherwise reached via machine/deep learning solutions, though at the expense of interpretation. The recent development of explainable AI is the key to combine both strengths. In this work, we explore this combination in the context of HMP susceptibility modeling. Specifically, we demonstrate the extent to which one can enter a new level of data-driven interpretation, supporting the decision-making process behind disaster risk mitigation and prevention actions. (c) 2024 China University of Geosciences (Beijing) and Peking University. Published by Elsevier B.V. on behalf of China University of Geosciences (Beijing). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
| WOS关键词 | LANDSLIDE SUSCEPTIBILITY ; FLOOD SUSCEPTIBILITY ; PREDICTION MODELS ; FLASH FLOODS ; HAZARD ; CHINA ; CATCHMENTS ; EVOLUTION ; QUALITY |
| WOS研究方向 | Geology |
| 语种 | 英语 |
| 出版者 | CHINA UNIV GEOSCIENCES, BEIJING |
| WOS记录号 | WOS:001182591200001 |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/203313]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 作者单位 | 1.Beijing Normal Univ, Fac Geog Sci, Ctr Geodata & Anal, Beijing 100875, Peoples R China 2.Beijing Normal Univ, Key Lab Environm Change & Nat Disaster, Beijing 100875, Peoples R China 3.Beijing Normal Univ, State Key Lab Earth Surface Proc & Resource Ecol, Beijing 100875, Peoples R China 4.Collaborat Innovat Ctr South China Sea Studies, Nanjing 210093, Peoples R China 5.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing 210023, Peoples R China 6.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 7.Univ Twente, Fac Geoinformat Sci & Earth Observat ITC, POB 217, NL-AE 7500 Enschede, Netherlands 8.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 9.Northeast Normal Univ, Sch Geog Sci, Key Lab Geog Proc & Ecol Secur Changbai Mt, Minist Educ, Changchun 130024, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Nan,Zhang, Hongyan,Dahal, Ashok,et al. On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values[J]. GEOSCIENCE FRONTIERS,2024,15(4):101800. |
| APA | Wang, Nan,Zhang, Hongyan,Dahal, Ashok,Cheng, Weiming,Zhao, Min,&Lombardo, Luigi.(2024).On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values.GEOSCIENCE FRONTIERS,15(4),101800. |
| MLA | Wang, Nan,et al."On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values".GEOSCIENCE FRONTIERS 15.4(2024):101800. |
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。