Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand
In mountainous terrain, landslides are common, particularly in intermontane basin locations. Such regions can adversely affect both human beings and the environment. In the assessment of landslide susceptibility, machine learning (ML) algorithms are increasingly popular due to their compatibility wi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Mahidol University
2024-03-01
|
| Series: | Environment and Natural Resources Journal |
| Subjects: | |
| Online Access: | https://ph02.tci-thaijo.org/index.php/ennrj/article/view/250842/170213 |
| _version_ | 1827317742404894720 |
|---|---|
| author | Kritchayan Intarat Patimakorn Yoomee Areewan Hussadin Wanjai Lamprom |
| author_facet | Kritchayan Intarat Patimakorn Yoomee Areewan Hussadin Wanjai Lamprom |
| author_sort | Kritchayan Intarat |
| collection | DOAJ |
| description | In mountainous terrain, landslides are common, particularly in intermontane basin locations. Such regions can adversely affect both human beings and the environment. In the assessment of landslide susceptibility, machine learning (ML) algorithms are increasingly popular due to their compatibility with geospatial data and tools. Herein, this study evaluated the performance of four ML algorithms: namely, random forest (RF), gradient boost (GB), extreme gradient boost (XGB), and stacking ensemble (STK). These algorithms were implemented to create a practical model of landslide susceptibility. The site under investigation is in the province of Chiang Mai, an intermontane basin area in northern Thailand where populations are settled. To address issues of multicollinearity, the variance inflation factor (VIF) was used. Eight out of fourteen factors were selected for examination; hyperparameters of each model were tested to acquire the best combination. Results indicated that the STK model outperforms all other models, providing evaluation metrics (precision, recall, F1-score, and overall accuracy) of 82.92%, 81.18%, 82.04%, and 81.75%, respectively. The area under the receiver operating characteristic (ROC) curve also reveals the high efficiency of the model, achieving 0.8928. However, further analysis of the appropriate model or base learner is necessary for achieving even higher predictive results. |
| first_indexed | 2024-04-24T23:46:03Z |
| format | Article |
| id | doaj.art-e7598b5eba1540239fd6be276901f650 |
| institution | Directory Open Access Journal |
| issn | 1686-5456 2408-2384 |
| language | English |
| last_indexed | 2024-04-24T23:46:03Z |
| publishDate | 2024-03-01 |
| publisher | Mahidol University |
| record_format | Article |
| series | Environment and Natural Resources Journal |
| spelling | doaj.art-e7598b5eba1540239fd6be276901f6502024-03-15T07:51:47ZengMahidol UniversityEnvironment and Natural Resources Journal1686-54562408-23842024-03-0122215817010.32526/ennrj/22/20230241Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern ThailandKritchayan Intarat0Patimakorn Yoomee1Areewan Hussadin2Wanjai Lamprom3Department of Geography, Faculty of Liberal Arts, Thammasat University, ThailandDepartment of Geography, Faculty of Liberal Arts, Thammasat University, ThailandResearch Unit in Geospatial Applications (Capybara Geo Lab), Faculty of Liberal Arts, Thammasat University, ThailandFaculty of Liberal Arts, Rajamangala University of Technology Thanyaburi, ThailandIn mountainous terrain, landslides are common, particularly in intermontane basin locations. Such regions can adversely affect both human beings and the environment. In the assessment of landslide susceptibility, machine learning (ML) algorithms are increasingly popular due to their compatibility with geospatial data and tools. Herein, this study evaluated the performance of four ML algorithms: namely, random forest (RF), gradient boost (GB), extreme gradient boost (XGB), and stacking ensemble (STK). These algorithms were implemented to create a practical model of landslide susceptibility. The site under investigation is in the province of Chiang Mai, an intermontane basin area in northern Thailand where populations are settled. To address issues of multicollinearity, the variance inflation factor (VIF) was used. Eight out of fourteen factors were selected for examination; hyperparameters of each model were tested to acquire the best combination. Results indicated that the STK model outperforms all other models, providing evaluation metrics (precision, recall, F1-score, and overall accuracy) of 82.92%, 81.18%, 82.04%, and 81.75%, respectively. The area under the receiver operating characteristic (ROC) curve also reveals the high efficiency of the model, achieving 0.8928. However, further analysis of the appropriate model or base learner is necessary for achieving even higher predictive results.https://ph02.tci-thaijo.org/index.php/ennrj/article/view/250842/170213landslide susceptibilitymachine learningensemble modelintermontane basinchiang mai |
| spellingShingle | Kritchayan Intarat Patimakorn Yoomee Areewan Hussadin Wanjai Lamprom Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand Environment and Natural Resources Journal landslide susceptibility machine learning ensemble model intermontane basin chiang mai |
| title | Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand |
| title_full | Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand |
| title_fullStr | Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand |
| title_full_unstemmed | Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand |
| title_short | Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand |
| title_sort | assessment of landslide susceptibility in the intermontane basin area of northern thailand |
| topic | landslide susceptibility machine learning ensemble model intermontane basin chiang mai |
| url | https://ph02.tci-thaijo.org/index.php/ennrj/article/view/250842/170213 |
| work_keys_str_mv | AT kritchayanintarat assessmentoflandslidesusceptibilityintheintermontanebasinareaofnorthernthailand AT patimakornyoomee assessmentoflandslidesusceptibilityintheintermontanebasinareaofnorthernthailand AT areewanhussadin assessmentoflandslidesusceptibilityintheintermontanebasinareaofnorthernthailand AT wanjailamprom assessmentoflandslidesusceptibilityintheintermontanebasinareaofnorthernthailand |