Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China
Flash flood, one of the most devastating weather-related hazards in the world, has become more and more frequent in past decades. For the purpose of flood mitigation, it is necessary to understand the distribution of flash flood risk. In this study, artificial intelligence (Least squares support vec...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/11/2/170 |
| _version_ | 1818083317036089344 |
|---|---|
| author | Meihong Ma Changjun Liu Gang Zhao Hongjie Xie Pengfei Jia Dacheng Wang Huixiao Wang Yang Hong |
| author_facet | Meihong Ma Changjun Liu Gang Zhao Hongjie Xie Pengfei Jia Dacheng Wang Huixiao Wang Yang Hong |
| author_sort | Meihong Ma |
| collection | DOAJ |
| description | Flash flood, one of the most devastating weather-related hazards in the world, has become more and more frequent in past decades. For the purpose of flood mitigation, it is necessary to understand the distribution of flash flood risk. In this study, artificial intelligence (Least squares support vector machine: LSSVM) and classical canonical method (Logistic regression: LR) are used to assess the flash flood risk in the Yunnan Province based on historical flash flood records and 13 meteorological, topographical, hydrological and anthropological factors. Results indicate that: (1) the LSSVM with Radial basis function (RBF) Kernel works the best (Accuracy = 0.79) and the LR is the worst (Accuracy = 0.75) in testing; (2) flash flood risk distribution identified by the LSSVM in Yunnan province is near normal distribution; (3) the high-risk areas are mainly concentrated in the central and southeastern regions, where with a large curve number; and (4) the impact factors contributing the flash flood risk map from higher to low are: Curve number > Digital elevation > Slope > River density > Flash Flood preventions > Topographic Wetness Index > annual maximum 24 h precipitation > annual maximum 3 h precipitation. |
| first_indexed | 2024-12-10T19:36:04Z |
| format | Article |
| id | doaj.art-2edfb63170954565bcf9052c96f12093 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-10T19:36:04Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2edfb63170954565bcf9052c96f120932022-12-22T01:36:07ZengMDPI AGRemote Sensing2072-42922019-01-0111217010.3390/rs11020170rs11020170Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, ChinaMeihong Ma0Changjun Liu1Gang Zhao2Hongjie Xie3Pengfei Jia4Dacheng Wang5Huixiao Wang6Yang Hong7China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaChina Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaSchool of Geographical Sciences, University of Bristol, Bristol BS8 1SS, UKDepartment of Geological Sciences University of Texas at San Antonio, San Antonio, TX 78249, USACITIC Construction Co., Ltd., Beijing 100027, ChinaLab of Spatial Information Integration, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, ChinaCollege of water sciences, Beijing Normal University, Beijing 100875, ChinaSchool of Earth and Space Sciences, Peking University, Beijing 100871, ChinaFlash flood, one of the most devastating weather-related hazards in the world, has become more and more frequent in past decades. For the purpose of flood mitigation, it is necessary to understand the distribution of flash flood risk. In this study, artificial intelligence (Least squares support vector machine: LSSVM) and classical canonical method (Logistic regression: LR) are used to assess the flash flood risk in the Yunnan Province based on historical flash flood records and 13 meteorological, topographical, hydrological and anthropological factors. Results indicate that: (1) the LSSVM with Radial basis function (RBF) Kernel works the best (Accuracy = 0.79) and the LR is the worst (Accuracy = 0.75) in testing; (2) flash flood risk distribution identified by the LSSVM in Yunnan province is near normal distribution; (3) the high-risk areas are mainly concentrated in the central and southeastern regions, where with a large curve number; and (4) the impact factors contributing the flash flood risk map from higher to low are: Curve number > Digital elevation > Slope > River density > Flash Flood preventions > Topographic Wetness Index > annual maximum 24 h precipitation > annual maximum 3 h precipitation.http://www.mdpi.com/2072-4292/11/2/170flash floodriskLSSVMChina |
| spellingShingle | Meihong Ma Changjun Liu Gang Zhao Hongjie Xie Pengfei Jia Dacheng Wang Huixiao Wang Yang Hong Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China Remote Sensing flash flood risk LSSVM China |
| title | Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China |
| title_full | Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China |
| title_fullStr | Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China |
| title_full_unstemmed | Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China |
| title_short | Flash Flood Risk Analysis Based on Machine Learning Techniques in the Yunnan Province, China |
| title_sort | flash flood risk analysis based on machine learning techniques in the yunnan province china |
| topic | flash flood risk LSSVM China |
| url | http://www.mdpi.com/2072-4292/11/2/170 |
| work_keys_str_mv | AT meihongma flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT changjunliu flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT gangzhao flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT hongjiexie flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT pengfeijia flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT dachengwang flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT huixiaowang flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina AT yanghong flashfloodriskanalysisbasedonmachinelearningtechniquesintheyunnanprovincechina |