Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing
As a common geological hazard, debris flow is widely distributed around the world. Meanwhile, due to the influence of many factors such as geology, geomorphology and climate, the occurrence frequency and main inducing factors are different in different places. Therefore, the evaluation of debris flo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/4/705 |
| _version_ | 1797617691930918912 |
|---|---|
| author | Feifan Gu Jianping Chen Xiaohui Sun Yongchao Li Yiwei Zhang Qing Wang |
| author_facet | Feifan Gu Jianping Chen Xiaohui Sun Yongchao Li Yiwei Zhang Qing Wang |
| author_sort | Feifan Gu |
| collection | DOAJ |
| description | As a common geological hazard, debris flow is widely distributed around the world. Meanwhile, due to the influence of many factors such as geology, geomorphology and climate, the occurrence frequency and main inducing factors are different in different places. Therefore, the evaluation of debris flow sensitivity can provide a very important theoretical basis for disaster prevention and control. In this research, 43 debris flow gullies in Changping District, Beijing were cataloged and studied through field surveys and the 3S technology (GIS (Geography Information Systems), GPS (Global Positioning Systems), RS (Remote Sensing)). Eleven factors, including elevation, slope, plane curvature, profile curvature, roundness, geomorphic information entropy, TWI, SPI, TCI, NDVI and rainfall, were selected to establish a comprehensive evaluation index system. The watershed unit is directly related to the development and activities of debris flow, which can fully reflect the geomorphic and geological environment of debris flow. Therefore, the watershed unit was selected as the basic mapping unit to establish four evaluation models, namely ACA–PCA–FR (Analytic Hierarchy Process–Principal Component Analysis–Frequency Ratio), FR (Frequency Ratio), SVM (Support Vector Machines) and LR (Logistic Regression). In other words, this research evaluates debris flow susceptibility by comparingit with two traditional weight methods (ACA–PCA–FR and FR) and two machine learning methods (SVM and LR). The results show that the SVM evaluation model is superior to the other three models, and thevalueofthe area under the receiver-operating characteristic curve (AUC) is 0.889 from the receiver operating characteristic curve (ROC). It verifies that the SVM model has strong adaptability to small sample data. The study was divided into five regions, which were very low, low, moderate, high and very high, accounting for 22.31%, 25.04%, 17.66%, 18.85% and 16.14% of the total study area, respectively, by SVM model. The results obtained in this researchagree with the actual survey results, and can provide theoretical help for disaster prevention and reduction projects. |
| first_indexed | 2024-03-11T07:59:25Z |
| format | Article |
| id | doaj.art-180bf3d77c4d465b95612a2e0d63f376 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T07:59:25Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-180bf3d77c4d465b95612a2e0d63f3762023-11-16T23:52:21ZengMDPI AGWater2073-44412023-02-0115470510.3390/w15040705Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, BeijingFeifan Gu0Jianping Chen1Xiaohui Sun2Yongchao Li3Yiwei Zhang4Qing Wang5College of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaDepartment of Earth Sciences and Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaKey Laboratory of Shale Gas and Geoengineering, Institute of Geology and Geophysics, University of Chinese Academy of Sciences, Beijing 100029, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaCollege of Construction Engineering, Jilin University, Changchun 130026, ChinaAs a common geological hazard, debris flow is widely distributed around the world. Meanwhile, due to the influence of many factors such as geology, geomorphology and climate, the occurrence frequency and main inducing factors are different in different places. Therefore, the evaluation of debris flow sensitivity can provide a very important theoretical basis for disaster prevention and control. In this research, 43 debris flow gullies in Changping District, Beijing were cataloged and studied through field surveys and the 3S technology (GIS (Geography Information Systems), GPS (Global Positioning Systems), RS (Remote Sensing)). Eleven factors, including elevation, slope, plane curvature, profile curvature, roundness, geomorphic information entropy, TWI, SPI, TCI, NDVI and rainfall, were selected to establish a comprehensive evaluation index system. The watershed unit is directly related to the development and activities of debris flow, which can fully reflect the geomorphic and geological environment of debris flow. Therefore, the watershed unit was selected as the basic mapping unit to establish four evaluation models, namely ACA–PCA–FR (Analytic Hierarchy Process–Principal Component Analysis–Frequency Ratio), FR (Frequency Ratio), SVM (Support Vector Machines) and LR (Logistic Regression). In other words, this research evaluates debris flow susceptibility by comparingit with two traditional weight methods (ACA–PCA–FR and FR) and two machine learning methods (SVM and LR). The results show that the SVM evaluation model is superior to the other three models, and thevalueofthe area under the receiver-operating characteristic curve (AUC) is 0.889 from the receiver operating characteristic curve (ROC). It verifies that the SVM model has strong adaptability to small sample data. The study was divided into five regions, which were very low, low, moderate, high and very high, accounting for 22.31%, 25.04%, 17.66%, 18.85% and 16.14% of the total study area, respectively, by SVM model. The results obtained in this researchagree with the actual survey results, and can provide theoretical help for disaster prevention and reduction projects.https://www.mdpi.com/2073-4441/15/4/705debris flow susceptibility assessmentSVMLRACA–PCA–FRBeijing |
| spellingShingle | Feifan Gu Jianping Chen Xiaohui Sun Yongchao Li Yiwei Zhang Qing Wang Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing Water debris flow susceptibility assessment SVM LR ACA–PCA–FR Beijing |
| title | Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing |
| title_full | Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing |
| title_fullStr | Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing |
| title_full_unstemmed | Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing |
| title_short | Comparison of Machine Learning and Traditional Statistical Methods in Debris Flow Susceptibility Assessment: A Case Study of Changping District, Beijing |
| title_sort | comparison of machine learning and traditional statistical methods in debris flow susceptibility assessment a case study of changping district beijing |
| topic | debris flow susceptibility assessment SVM LR ACA–PCA–FR Beijing |
| url | https://www.mdpi.com/2073-4441/15/4/705 |
| work_keys_str_mv | AT feifangu comparisonofmachinelearningandtraditionalstatisticalmethodsindebrisflowsusceptibilityassessmentacasestudyofchangpingdistrictbeijing AT jianpingchen comparisonofmachinelearningandtraditionalstatisticalmethodsindebrisflowsusceptibilityassessmentacasestudyofchangpingdistrictbeijing AT xiaohuisun comparisonofmachinelearningandtraditionalstatisticalmethodsindebrisflowsusceptibilityassessmentacasestudyofchangpingdistrictbeijing AT yongchaoli comparisonofmachinelearningandtraditionalstatisticalmethodsindebrisflowsusceptibilityassessmentacasestudyofchangpingdistrictbeijing AT yiweizhang comparisonofmachinelearningandtraditionalstatisticalmethodsindebrisflowsusceptibilityassessmentacasestudyofchangpingdistrictbeijing AT qingwang comparisonofmachinelearningandtraditionalstatisticalmethodsindebrisflowsusceptibilityassessmentacasestudyofchangpingdistrictbeijing |