Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression
Landslides cause a considerable amount of damage around the world every year. Landslide susceptibility assessments are useful for the mitigation of the associated potential risks to local economic development, land use planning, and decision makers. The main aim of this study was to present a novel...
Main Authors: | , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-12-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/8/12/2540 |
_version_ | 1811193851759558656 |
---|---|
author | Wei Chen Himan Shahabi Shuai Zhang Khabat Khosravi Ataollah Shirzadi Kamran Chapi Binh Thai Pham Tingyu Zhang Lingyu Zhang Huichan Chai Jianquan Ma Yingtao Chen Xiaojing Wang Renwei Li Baharin Bin Ahmad |
author_facet | Wei Chen Himan Shahabi Shuai Zhang Khabat Khosravi Ataollah Shirzadi Kamran Chapi Binh Thai Pham Tingyu Zhang Lingyu Zhang Huichan Chai Jianquan Ma Yingtao Chen Xiaojing Wang Renwei Li Baharin Bin Ahmad |
author_sort | Wei Chen |
collection | DOAJ |
description | Landslides cause a considerable amount of damage around the world every year. Landslide susceptibility assessments are useful for the mitigation of the associated potential risks to local economic development, land use planning, and decision makers. The main aim of this study was to present a novel hybrid approach of bagging (B)-based kernel logistic regression (KLR), named the BKLR model, for spatial prediction of landslides in the Shangnan County, China. We first selected 15 conditioning factors for landslide susceptibility modeling. Then, the prediction capability of all conditioning factors was evaluated using the least square support vector machine method. Model validation and comparison were performed based on the area under the receiver operating characteristic curve and several statistical-based indexes, including positive predictive rate, negative predictive rate, sensitivity, specificity, kappa index, and root mean square error. Results indicated that the BKLR ensemble model outperformed and outclassed the KLR and the benchmark support vector machine model. Our findings overall confirmed that a combination of the meta model with a decision tree classifier based on a functional algorithm can decrease the over-fitting and variance problems of data, which could enhance the prediction power of the landslide model. The resultant susceptibility maps could be useful for hazard mitigation in the study area and other similar landslide-prone areas. |
first_indexed | 2024-04-12T00:16:20Z |
format | Article |
id | doaj.art-e0ed66e5708643458a8d453fffb27fac |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-04-12T00:16:20Z |
publishDate | 2018-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-e0ed66e5708643458a8d453fffb27fac2022-12-22T03:55:49ZengMDPI AGApplied Sciences2076-34172018-12-01812254010.3390/app8122540app8122540Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic RegressionWei Chen0Himan Shahabi1Shuai Zhang2Khabat Khosravi3Ataollah Shirzadi4Kamran Chapi5Binh Thai Pham6Tingyu Zhang7Lingyu Zhang8Huichan Chai9Jianquan Ma10Yingtao Chen11Xiaojing Wang12Renwei Li13Baharin Bin Ahmad14College of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaDepartments of Geomorphology, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaDepartment of Watershed Management, Faculty of Natural Resources, Sari Agricultural Sciences and Natural Resources University, Sari 48181-68984, IranDepartment of Rangeland and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranDepartment of Rangeland and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamSchool of Earth Science and Resources, Chang’an University, Xi’an 710064, ChinaCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Earth and Environment, Anhui University of Science & Technology, HuaiNan 232001, ChinaCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Geology & Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaFaculty of Built Environment and Surveying, Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, MalaysiaLandslides cause a considerable amount of damage around the world every year. Landslide susceptibility assessments are useful for the mitigation of the associated potential risks to local economic development, land use planning, and decision makers. The main aim of this study was to present a novel hybrid approach of bagging (B)-based kernel logistic regression (KLR), named the BKLR model, for spatial prediction of landslides in the Shangnan County, China. We first selected 15 conditioning factors for landslide susceptibility modeling. Then, the prediction capability of all conditioning factors was evaluated using the least square support vector machine method. Model validation and comparison were performed based on the area under the receiver operating characteristic curve and several statistical-based indexes, including positive predictive rate, negative predictive rate, sensitivity, specificity, kappa index, and root mean square error. Results indicated that the BKLR ensemble model outperformed and outclassed the KLR and the benchmark support vector machine model. Our findings overall confirmed that a combination of the meta model with a decision tree classifier based on a functional algorithm can decrease the over-fitting and variance problems of data, which could enhance the prediction power of the landslide model. The resultant susceptibility maps could be useful for hazard mitigation in the study area and other similar landslide-prone areas.https://www.mdpi.com/2076-3417/8/12/2540landslidemeta classifierprediction powerChina |
spellingShingle | Wei Chen Himan Shahabi Shuai Zhang Khabat Khosravi Ataollah Shirzadi Kamran Chapi Binh Thai Pham Tingyu Zhang Lingyu Zhang Huichan Chai Jianquan Ma Yingtao Chen Xiaojing Wang Renwei Li Baharin Bin Ahmad Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression Applied Sciences landslide meta classifier prediction power China |
title | Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression |
title_full | Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression |
title_fullStr | Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression |
title_full_unstemmed | Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression |
title_short | Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression |
title_sort | landslide susceptibility modeling based on gis and novel bagging based kernel logistic regression |
topic | landslide meta classifier prediction power China |
url | https://www.mdpi.com/2076-3417/8/12/2540 |
work_keys_str_mv | AT weichen landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT himanshahabi landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT shuaizhang landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT khabatkhosravi landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT ataollahshirzadi landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT kamranchapi landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT binhthaipham landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT tingyuzhang landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT lingyuzhang landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT huichanchai landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT jianquanma landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT yingtaochen landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT xiaojingwang landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT renweili landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression AT baharinbinahmad landslidesusceptibilitymodelingbasedongisandnovelbaggingbasedkernellogisticregression |