Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China
Debris flow susceptibility mapping is considered to be useful for hazard prevention and mitigation. As a frequent debris flow area, many hazardous events have occurred annually and caused a lot of damage in the Sichuan Province, China. Therefore, this study attempted to evaluate and compare the perf...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/2/295 |
id |
doaj-b325ea9ed7624460b0b87ab4a7c5859a |
---|---|
record_format |
Article |
spelling |
doaj-b325ea9ed7624460b0b87ab4a7c5859a2020-11-25T02:38:14ZengMDPI AGRemote Sensing2072-42922020-01-0112229510.3390/rs12020295rs12020295Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, ChinaKe Xiong0Basanta Raj Adhikari1Constantine A. Stamatopoulos2Yu Zhan3Shaolin Wu4Zhongtao Dong5Baofeng Di6Institute for Disaster Management and Reconstruction & Research Center for Integrated Disaster Risk Reduction and Emergency Management, Sichuan University, Chengdu 610207, ChinaInstitute for Disaster Management and Reconstruction & Research Center for Integrated Disaster Risk Reduction and Emergency Management, Sichuan University, Chengdu 610207, ChinaStamatopoulos and Associates Co. & Hellenic Open University, 11471 Athens, GreeceDepartment of Environmental Science and Engineering, College of Architecture and Environment, Sichuan University, Chengdu 610065, ChinaDepartment of Environmental Science and Engineering, College of Architecture and Environment, Sichuan University, Chengdu 610065, ChinaInstitute for Disaster Management and Reconstruction & Research Center for Integrated Disaster Risk Reduction and Emergency Management, Sichuan University, Chengdu 610207, ChinaInstitute for Disaster Management and Reconstruction & Research Center for Integrated Disaster Risk Reduction and Emergency Management, Sichuan University, Chengdu 610207, ChinaDebris flow susceptibility mapping is considered to be useful for hazard prevention and mitigation. As a frequent debris flow area, many hazardous events have occurred annually and caused a lot of damage in the Sichuan Province, China. Therefore, this study attempted to evaluate and compare the performance of four state-of-the-art machine-learning methods, namely Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and Boosted Regression Trees (BRT), for debris flow susceptibility mapping in this region. Four models were constructed based on the debris flow inventory and a range of causal factors. A variety of datasets was obtained through the combined application of remote sensing (RS) and geographic information system (GIS). The mean altitude, altitude difference, aridity index, and groove gradient played the most important role in the assessment. The performance of these modes was evaluated using predictive accuracy (ACC) and the area under the receiver operating characteristic curve (AUC). The results of this study showed that all four models were capable of producing accurate and robust debris flow susceptibility maps (ACC and AUC values were well above 0.75 and 0.80 separately). With an excellent spatial prediction capability and strong robustness, the BRT model (ACC = 0.781, AUC = 0.852) outperformed other models and was the ideal choice. Our results also exhibited the importance of selecting suitable mapping units and optimal predictors. Furthermore, the debris flow susceptibility maps of the Sichuan Province were produced, which can provide helpful data for assessing and mitigating debris flow hazards.https://www.mdpi.com/2072-4292/12/2/295debris flowsusceptibility mappingmachine learningremote sensinggeographical information system |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ke Xiong Basanta Raj Adhikari Constantine A. Stamatopoulos Yu Zhan Shaolin Wu Zhongtao Dong Baofeng Di |
spellingShingle |
Ke Xiong Basanta Raj Adhikari Constantine A. Stamatopoulos Yu Zhan Shaolin Wu Zhongtao Dong Baofeng Di Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China Remote Sensing debris flow susceptibility mapping machine learning remote sensing geographical information system |
author_facet |
Ke Xiong Basanta Raj Adhikari Constantine A. Stamatopoulos Yu Zhan Shaolin Wu Zhongtao Dong Baofeng Di |
author_sort |
Ke Xiong |
title |
Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China |
title_short |
Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China |
title_full |
Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China |
title_fullStr |
Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China |
title_full_unstemmed |
Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China |
title_sort |
comparison of different machine learning methods for debris flow susceptibility mapping: a case study in the sichuan province, china |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-01-01 |
description |
Debris flow susceptibility mapping is considered to be useful for hazard prevention and mitigation. As a frequent debris flow area, many hazardous events have occurred annually and caused a lot of damage in the Sichuan Province, China. Therefore, this study attempted to evaluate and compare the performance of four state-of-the-art machine-learning methods, namely Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and Boosted Regression Trees (BRT), for debris flow susceptibility mapping in this region. Four models were constructed based on the debris flow inventory and a range of causal factors. A variety of datasets was obtained through the combined application of remote sensing (RS) and geographic information system (GIS). The mean altitude, altitude difference, aridity index, and groove gradient played the most important role in the assessment. The performance of these modes was evaluated using predictive accuracy (ACC) and the area under the receiver operating characteristic curve (AUC). The results of this study showed that all four models were capable of producing accurate and robust debris flow susceptibility maps (ACC and AUC values were well above 0.75 and 0.80 separately). With an excellent spatial prediction capability and strong robustness, the BRT model (ACC = 0.781, AUC = 0.852) outperformed other models and was the ideal choice. Our results also exhibited the importance of selecting suitable mapping units and optimal predictors. Furthermore, the debris flow susceptibility maps of the Sichuan Province were produced, which can provide helpful data for assessing and mitigating debris flow hazards. |
topic |
debris flow susceptibility mapping machine learning remote sensing geographical information system |
url |
https://www.mdpi.com/2072-4292/12/2/295 |
work_keys_str_mv |
AT kexiong comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina AT basantarajadhikari comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina AT constantineastamatopoulos comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina AT yuzhan comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina AT shaolinwu comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina AT zhongtaodong comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina AT baofengdi comparisonofdifferentmachinelearningmethodsfordebrisflowsusceptibilitymappingacasestudyinthesichuanprovincechina |
_version_ |
1724792030865915904 |