Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods
The Hengduan Mountains region (HMR) is vulnerable to flash flood disasters, which account for the largest proportion of flood-related fatalities in China. Flash flood regionalization, which divides a region into homogeneous subdivisions based on flash flood-inducing factors, provides insights for th...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/6/946 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850088377385222144 |
|---|---|
| author | Yifan Li Chendi Zhang Peng Cui Marwan Hassan Zhongjie Duan Suman Bhattacharyya Shunyu Yao Yang Zhao |
| author_facet | Yifan Li Chendi Zhang Peng Cui Marwan Hassan Zhongjie Duan Suman Bhattacharyya Shunyu Yao Yang Zhao |
| author_sort | Yifan Li |
| collection | DOAJ |
| description | The Hengduan Mountains region (HMR) is vulnerable to flash flood disasters, which account for the largest proportion of flood-related fatalities in China. Flash flood regionalization, which divides a region into homogeneous subdivisions based on flash flood-inducing factors, provides insights for the spatial distribution patterns of flash flood risk, especially in ungauged areas. However, existing methods for flash flood regionalization have not fully reflected the spatial topology structure of the inputted geographical data. To address this issue, this study proposed a novel framework combining a state-of-the-art unsupervised Graph Neural Network (GNN) method, Dink-Net, and Shapley Additive exPlanations (SHAP) for flash flood regionalization in the HMR. A comprehensive dataset of flash flood inducing factors was first established, covering geomorphology, climate, meteorology, hydrology, and surface conditions. The performances of two classic machine learning methods (K-means and Self-organizing feature map) and three GNN methods (Deep Graph Infomax (DGI), Deep Modularity Networks (DMoN), and Dilation shrink Network (Dink-Net)) were compared for flash-flood regionalization, and the Dink-Net model outperformed the others. The SHAP model was then applied to quantify the impact of all the inducing factors on the regionalization results by Dink-Net. The newly developed framework captured the spatial interactions of the inducing factors and characterized the spatial distribution patterns of the factors. The unsupervised Dink-Net model allowed the framework to be independent from historical flash flood data, which would facilitate its application in ungauged mountainous areas. The impact analysis highlights the significant positive influence of extreme rainfall on flash floods across the entire HMR. The pronounced positive impact of soil moisture and saturated hydraulic conductivity in the areas with a concentration of historical flash flood events, together with the positive impact of topography (elevation) in the transition zone from the Qinghai–Tibet Plateau to the Sichuan Basin, have also been revealed. The results of this study provide technical support and a scientific basis for flood control and disaster reduction measures in mountain areas according to local inducing conditions. |
| format | Article |
| id | doaj-art-e5227dd6f81f436092c93fac16cd3d65 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-e5227dd6f81f436092c93fac16cd3d652025-08-20T02:43:02ZengMDPI AGRemote Sensing2072-42922025-03-0117694610.3390/rs17060946Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP MethodsYifan Li0Chendi Zhang1Peng Cui2Marwan Hassan3Zhongjie Duan4Suman Bhattacharyya5Shunyu Yao6Yang Zhao7Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaDepartment of Geography, University of British Columbia, Vancouver, BC V6T1Z2, CanadaDepartment of Data Science and Engineering, East China Normal University, Shanghai 200062, ChinaDepartment of Geography, University of British Columbia, Vancouver, BC V6T1Z2, CanadaChina Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaSichuan Zipingpu Development Co., Ltd., Chengdu 610091, ChinaThe Hengduan Mountains region (HMR) is vulnerable to flash flood disasters, which account for the largest proportion of flood-related fatalities in China. Flash flood regionalization, which divides a region into homogeneous subdivisions based on flash flood-inducing factors, provides insights for the spatial distribution patterns of flash flood risk, especially in ungauged areas. However, existing methods for flash flood regionalization have not fully reflected the spatial topology structure of the inputted geographical data. To address this issue, this study proposed a novel framework combining a state-of-the-art unsupervised Graph Neural Network (GNN) method, Dink-Net, and Shapley Additive exPlanations (SHAP) for flash flood regionalization in the HMR. A comprehensive dataset of flash flood inducing factors was first established, covering geomorphology, climate, meteorology, hydrology, and surface conditions. The performances of two classic machine learning methods (K-means and Self-organizing feature map) and three GNN methods (Deep Graph Infomax (DGI), Deep Modularity Networks (DMoN), and Dilation shrink Network (Dink-Net)) were compared for flash-flood regionalization, and the Dink-Net model outperformed the others. The SHAP model was then applied to quantify the impact of all the inducing factors on the regionalization results by Dink-Net. The newly developed framework captured the spatial interactions of the inducing factors and characterized the spatial distribution patterns of the factors. The unsupervised Dink-Net model allowed the framework to be independent from historical flash flood data, which would facilitate its application in ungauged mountainous areas. The impact analysis highlights the significant positive influence of extreme rainfall on flash floods across the entire HMR. The pronounced positive impact of soil moisture and saturated hydraulic conductivity in the areas with a concentration of historical flash flood events, together with the positive impact of topography (elevation) in the transition zone from the Qinghai–Tibet Plateau to the Sichuan Basin, have also been revealed. The results of this study provide technical support and a scientific basis for flood control and disaster reduction measures in mountain areas according to local inducing conditions.https://www.mdpi.com/2072-4292/17/6/946flash floodGraph Neural Network (GNN)regionalizationthe Hengduan Mountains region (HMR)interpretation model |
| spellingShingle | Yifan Li Chendi Zhang Peng Cui Marwan Hassan Zhongjie Duan Suman Bhattacharyya Shunyu Yao Yang Zhao Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods Remote Sensing flash flood Graph Neural Network (GNN) regionalization the Hengduan Mountains region (HMR) interpretation model |
| title | Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods |
| title_full | Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods |
| title_fullStr | Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods |
| title_full_unstemmed | Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods |
| title_short | Flash Flood Regionalization for the Hengduan Mountains Region, China, Combining GNN and SHAP Methods |
| title_sort | flash flood regionalization for the hengduan mountains region china combining gnn and shap methods |
| topic | flash flood Graph Neural Network (GNN) regionalization the Hengduan Mountains region (HMR) interpretation model |
| url | https://www.mdpi.com/2072-4292/17/6/946 |
| work_keys_str_mv | AT yifanli flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT chendizhang flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT pengcui flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT marwanhassan flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT zhongjieduan flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT sumanbhattacharyya flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT shunyuyao flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods AT yangzhao flashfloodregionalizationforthehengduanmountainsregionchinacombininggnnandshapmethods |