Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea
Landslides are a major natural hazard that can significantly damage infrastructure and cause loss of life. In South Korea, the current landslide susceptibility mapping (LSM) approach is mainly based on statistical techniques (logistic regression (LR) analysis). According to previous studies, this me...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2023.1268501/full |
| _version_ | 1797679234022375424 |
|---|---|
| author | Xuan-Hien Le Xuan-Hien Le Song Eu Chanul Choi Duc Hai Nguyen Minho Yeon Giha Lee |
| author_facet | Xuan-Hien Le Xuan-Hien Le Song Eu Chanul Choi Duc Hai Nguyen Minho Yeon Giha Lee |
| author_sort | Xuan-Hien Le |
| collection | DOAJ |
| description | Landslides are a major natural hazard that can significantly damage infrastructure and cause loss of life. In South Korea, the current landslide susceptibility mapping (LSM) approach is mainly based on statistical techniques (logistic regression (LR) analysis). According to previous studies, this method has achieved an accuracy of approximately 75.2%. In this paper, we expand upon this traditional approach by comparing the performance of six machine learning (ML) algorithms for LSM in Inje County, South Korea. The study employed a combination of geographical data gathered from 2005 to 2019 to train and evaluate six algorithms, including LR, Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGB). The effectiveness of these models was measured by various criteria, such as the percentage of correct classification (PCC) score, F1 score, and Kappa score. The results demonstrated that the PCC and F1 scores of the six models fell between [0.869–0.941] and [0.857–0.940], respectively. RF and XGB had the highest PCC and F1 scores of 0.939 and 0.941, respectively. This study indicates that ML can be a valuable technique for high-resolution LSM in South Korea instead of the current approach. |
| first_indexed | 2024-03-11T23:11:32Z |
| format | Article |
| id | doaj.art-7644444193d942919b7bb0d435310297 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-03-11T23:11:32Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-7644444193d942919b7bb0d4353102972023-09-21T08:09:48ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-09-011110.3389/feart.2023.12685011268501Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South KoreaXuan-Hien Le0Xuan-Hien Le1Song Eu2Chanul Choi3Duc Hai Nguyen4Minho Yeon5Giha Lee6Department of Advanced Science and Technology Convergence, Kyungpook National University, Sangju, Republic of KoreaFaculty of Water Resources Engineering, Thuyloi University, Hanoi, VietnamDepartment of Forest Environment and Conservation, National Institute of Forest Science, Seoul, Republic of KoreaDepartment of Advanced Science and Technology Convergence, Kyungpook National University, Sangju, Republic of KoreaFaculty of Water Resources Engineering, Thuyloi University, Hanoi, VietnamDepartment of Advanced Science and Technology Convergence, Kyungpook National University, Sangju, Republic of KoreaDepartment of Advanced Science and Technology Convergence, Kyungpook National University, Sangju, Republic of KoreaLandslides are a major natural hazard that can significantly damage infrastructure and cause loss of life. In South Korea, the current landslide susceptibility mapping (LSM) approach is mainly based on statistical techniques (logistic regression (LR) analysis). According to previous studies, this method has achieved an accuracy of approximately 75.2%. In this paper, we expand upon this traditional approach by comparing the performance of six machine learning (ML) algorithms for LSM in Inje County, South Korea. The study employed a combination of geographical data gathered from 2005 to 2019 to train and evaluate six algorithms, including LR, Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGB). The effectiveness of these models was measured by various criteria, such as the percentage of correct classification (PCC) score, F1 score, and Kappa score. The results demonstrated that the PCC and F1 scores of the six models fell between [0.869–0.941] and [0.857–0.940], respectively. RF and XGB had the highest PCC and F1 scores of 0.939 and 0.941, respectively. This study indicates that ML can be a valuable technique for high-resolution LSM in South Korea instead of the current approach.https://www.frontiersin.org/articles/10.3389/feart.2023.1268501/fulldisaster managementextreme gradient boosting (XGB)feature importancelandslidelandslide probabilitylandslide susceptibility mapping (LSM) |
| spellingShingle | Xuan-Hien Le Xuan-Hien Le Song Eu Chanul Choi Duc Hai Nguyen Minho Yeon Giha Lee Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea Frontiers in Earth Science disaster management extreme gradient boosting (XGB) feature importance landslide landslide probability landslide susceptibility mapping (LSM) |
| title | Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea |
| title_full | Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea |
| title_fullStr | Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea |
| title_full_unstemmed | Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea |
| title_short | Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea |
| title_sort | machine learning for high resolution landslide susceptibility mapping case study in inje county south korea |
| topic | disaster management extreme gradient boosting (XGB) feature importance landslide landslide probability landslide susceptibility mapping (LSM) |
| url | https://www.frontiersin.org/articles/10.3389/feart.2023.1268501/full |
| work_keys_str_mv | AT xuanhienle machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea AT xuanhienle machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea AT songeu machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea AT chanulchoi machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea AT duchainguyen machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea AT minhoyeon machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea AT gihalee machinelearningforhighresolutionlandslidesusceptibilitymappingcasestudyininjecountysouthkorea |