Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway
The China–Pakistan Karakoram Highway is an important land route from China to South Asia and the Middle East via Pakistan. Due to the extremely hazardous geological environment around the highway, landslides, debris flows, collapses, and subsidence are frequent. Among them, debris flows are one of t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/18/2933 |
| _version_ | 1797554070565683200 |
|---|---|
| author | Feng Qing Yan Zhao Xingmin Meng Xiaojun Su Tianjun Qi Dongxia Yue |
| author_facet | Feng Qing Yan Zhao Xingmin Meng Xiaojun Su Tianjun Qi Dongxia Yue |
| author_sort | Feng Qing |
| collection | DOAJ |
| description | The China–Pakistan Karakoram Highway is an important land route from China to South Asia and the Middle East via Pakistan. Due to the extremely hazardous geological environment around the highway, landslides, debris flows, collapses, and subsidence are frequent. Among them, debris flows are one of the most serious geological hazards on the Karakoram Highway, and they often cause interruptions to traffic and casualties. Therefore, the development of debris flow susceptibility mapping along the highway can potentially facilitate its safe operation. In this study, we used remote sensing, GIS, and machine learning techniques to map debris flow susceptibility along the Karakoram Highway in areas where observation data are scarce and difficult to obtain by field survey. First, the distribution of 544 catchments which are prone to debris flow were identified through visual interpretation of remote sensing images. The factors influencing debris flow susceptibility were then analyzed, and a total of 17 parameters related to geomorphology, soil materials, and triggering conditions were selected. Model training was based on multiple common machine learning methods, including Ensemble Methods, Gaussian Processes, Generalized Linear models, Navies Bayes, Nearest Neighbors, Support Vector Machines, Trees, Discriminant Analysis, and eXtreme Gradient Boosting. Support Vector Classification (SVC) was chosen as the final model after evaluation; its accuracy (ACC) was 0.91, and the area under the ROC curve (AUC) was 0.96. Among the factors involved in SVC, the Melton Ratio (<i>MR</i>) was the most important, followed by drainage density (<i>DD</i>), Hypsometric Integral (<i>HI</i>), and average slope (<i>AS</i>), indicating that geomorphic conditions play an important role in predicting debris flow susceptibility in the study area. SVC was used to map debris flow susceptibility in the study area, and the results will potentially facilitate the safe operation of the highway. |
| first_indexed | 2024-03-10T16:26:35Z |
| format | Article |
| id | doaj.art-8c70cd46935140deaa163ea7584122cd |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T16:26:35Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8c70cd46935140deaa163ea7584122cd2023-11-20T13:12:16ZengMDPI AGRemote Sensing2072-42922020-09-011218293310.3390/rs12182933Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram HighwayFeng Qing0Yan Zhao1Xingmin Meng2Xiaojun Su3Tianjun Qi4Dongxia Yue5College of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, ChinaSchool of Earth Sciences, Lanzhou University, Lanzhou 730000, ChinaCollege of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, ChinaCollege of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, ChinaCollege of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, ChinaCollege of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, ChinaThe China–Pakistan Karakoram Highway is an important land route from China to South Asia and the Middle East via Pakistan. Due to the extremely hazardous geological environment around the highway, landslides, debris flows, collapses, and subsidence are frequent. Among them, debris flows are one of the most serious geological hazards on the Karakoram Highway, and they often cause interruptions to traffic and casualties. Therefore, the development of debris flow susceptibility mapping along the highway can potentially facilitate its safe operation. In this study, we used remote sensing, GIS, and machine learning techniques to map debris flow susceptibility along the Karakoram Highway in areas where observation data are scarce and difficult to obtain by field survey. First, the distribution of 544 catchments which are prone to debris flow were identified through visual interpretation of remote sensing images. The factors influencing debris flow susceptibility were then analyzed, and a total of 17 parameters related to geomorphology, soil materials, and triggering conditions were selected. Model training was based on multiple common machine learning methods, including Ensemble Methods, Gaussian Processes, Generalized Linear models, Navies Bayes, Nearest Neighbors, Support Vector Machines, Trees, Discriminant Analysis, and eXtreme Gradient Boosting. Support Vector Classification (SVC) was chosen as the final model after evaluation; its accuracy (ACC) was 0.91, and the area under the ROC curve (AUC) was 0.96. Among the factors involved in SVC, the Melton Ratio (<i>MR</i>) was the most important, followed by drainage density (<i>DD</i>), Hypsometric Integral (<i>HI</i>), and average slope (<i>AS</i>), indicating that geomorphic conditions play an important role in predicting debris flow susceptibility in the study area. SVC was used to map debris flow susceptibility in the study area, and the results will potentially facilitate the safe operation of the highway.https://www.mdpi.com/2072-4292/12/18/2933debris flowmachine learningsusceptibility mappingKarakoram Highway |
| spellingShingle | Feng Qing Yan Zhao Xingmin Meng Xiaojun Su Tianjun Qi Dongxia Yue Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway Remote Sensing debris flow machine learning susceptibility mapping Karakoram Highway |
| title | Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway |
| title_full | Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway |
| title_fullStr | Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway |
| title_full_unstemmed | Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway |
| title_short | Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway |
| title_sort | application of machine learning to debris flow susceptibility mapping along the china pakistan karakoram highway |
| topic | debris flow machine learning susceptibility mapping Karakoram Highway |
| url | https://www.mdpi.com/2072-4292/12/18/2933 |
| work_keys_str_mv | AT fengqing applicationofmachinelearningtodebrisflowsusceptibilitymappingalongthechinapakistankarakoramhighway AT yanzhao applicationofmachinelearningtodebrisflowsusceptibilitymappingalongthechinapakistankarakoramhighway AT xingminmeng applicationofmachinelearningtodebrisflowsusceptibilitymappingalongthechinapakistankarakoramhighway AT xiaojunsu applicationofmachinelearningtodebrisflowsusceptibilitymappingalongthechinapakistankarakoramhighway AT tianjunqi applicationofmachinelearningtodebrisflowsusceptibilitymappingalongthechinapakistankarakoramhighway AT dongxiayue applicationofmachinelearningtodebrisflowsusceptibilitymappingalongthechinapakistankarakoramhighway |