K. Intarat, Patimakorn Yoomee, Areewan Hussadin, Wanjai Lamprom
{"title":"Assessment of Landslide Susceptibility in the Intermontane Basin Area of Northern Thailand","authors":"K. Intarat, Patimakorn Yoomee, Areewan Hussadin, Wanjai Lamprom","doi":"10.32526/ennrj/22/20230241","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":11784,"journal":{"name":"Environment and Natural Resources Journal","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environment and Natural Resources Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.32526/ennrj/22/20230241","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Environmental Science","Score":null,"Total":0}
引用次数: 0
Abstract
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.
期刊介绍:
The Environment and Natural Resources Journal is a peer-reviewed journal, which provides insight scientific knowledge into the diverse dimensions of integrated environmental and natural resource management. The journal aims to provide a platform for exchange and distribution of the knowledge and cutting-edge research in the fields of environmental science and natural resource management to academicians, scientists and researchers. The journal accepts a varied array of manuscripts on all aspects of environmental science and natural resource management. The journal scope covers the integration of multidisciplinary sciences for prevention, control, treatment, environmental clean-up and restoration. The study of the existing or emerging problems of environment and natural resources in the region of Southeast Asia and the creation of novel knowledge and/or recommendations of mitigation measures for sustainable development policies are emphasized. The subject areas are diverse, but specific topics of interest include: -Biodiversity -Climate change -Detection and monitoring of polluted sources e.g., industry, mining -Disaster e.g., forest fire, flooding, earthquake, tsunami, or tidal wave -Ecological/Environmental modelling -Emerging contaminants/hazardous wastes investigation and remediation -Environmental dynamics e.g., coastal erosion, sea level rise -Environmental assessment tools, policy and management e.g., GIS, remote sensing, Environmental -Management System (EMS) -Environmental pollution and other novel solutions to pollution -Remediation technology of contaminated environments -Transboundary pollution -Waste and wastewater treatments and disposal technology