Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms
Landslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting in significant damage and fatalities. The primary purpose of this study was to assess the efficacy of three machine learning algorithms (MLAs) for landslide susceptibility mapping...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/12/3112 |
| _version_ | 1797592803985850368 |
|---|---|
| author | Himan Shahabi Reza Ahmadi Mohsen Alizadeh Mazlan Hashim Nadhir Al-Ansari Ataollah Shirzadi Isabelle D. Wolf Effi Helmy Ariffin |
| author_facet | Himan Shahabi Reza Ahmadi Mohsen Alizadeh Mazlan Hashim Nadhir Al-Ansari Ataollah Shirzadi Isabelle D. Wolf Effi Helmy Ariffin |
| author_sort | Himan Shahabi |
| collection | DOAJ |
| description | Landslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting in significant damage and fatalities. The primary purpose of this study was to assess the efficacy of three machine learning algorithms (MLAs) for landslide susceptibility mapping including random forest (RF), decision tree (DT), and support vector machine (SVM). We selected a case study region that is frequently affected by landslides, the important Kamyaran–Sarvabad road in the Kurdistan province of Iran. Altogether, 14 landslide evaluation factors were input into the MLAs including slope, aspect, elevation, river density, distance to river, distance to fault, fault density, distance to road, road density, land use, slope curvature, lithology, stream power index (SPI), and topographic wetness index (TWI). We identified 64 locations of landslides by field survey of which 70% were randomly employed for building and training the three MLAs while the remaining locations were used for validation. The area under the receiver operating characteristics (AUC) reached a value of 0.94 for the decision tree compared to 0.82 for the random forest, and 0.75 for support vector machines model. Thus, the decision tree model was most accurate in identifying the areas at risk for future landslides. The obtained results may inform geoscientists and those in decision-making roles for landslide management. |
| first_indexed | 2024-03-11T01:59:20Z |
| format | Article |
| id | doaj.art-d5b210653cd042bfa1825d31423e371e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T01:59:20Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d5b210653cd042bfa1825d31423e371e2023-11-18T12:26:37ZengMDPI AGRemote Sensing2072-42922023-06-011512311210.3390/rs15123112Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning AlgorithmsHiman Shahabi0Reza Ahmadi1Mohsen Alizadeh2Mazlan Hashim3Nadhir Al-Ansari4Ataollah Shirzadi5Isabelle D. Wolf6Effi Helmy Ariffin7Department of Geomorphology, Faculty of Natural Resources, University of Kurdistan, Sanandaj 6617715175, IranDepartment of Geomorphology, Faculty of Natural Resources, University of Kurdistan, Sanandaj 6617715175, IranInstitute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu (UMT), Kuala Nerus 21030, MalaysiaGeoscience and Digital Earth Centre (INSTeG), Research Institute for Sustainability and Environment (RISE), Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, MalaysiaCivil, Environmental and Natural Resources Engineering, Lulea University of Technology, 97187 Lulea, SwedenDepartment of Rangeland and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Sanandaj 6617715175, IranAustralian Centre for Culture, Environment, Society and Space, School of Geography and Sustainable Communities, University of Wollongong, Wollongong, NSW 2522, AustraliaInstitute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu (UMT), Kuala Nerus 21030, MalaysiaLandslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting in significant damage and fatalities. The primary purpose of this study was to assess the efficacy of three machine learning algorithms (MLAs) for landslide susceptibility mapping including random forest (RF), decision tree (DT), and support vector machine (SVM). We selected a case study region that is frequently affected by landslides, the important Kamyaran–Sarvabad road in the Kurdistan province of Iran. Altogether, 14 landslide evaluation factors were input into the MLAs including slope, aspect, elevation, river density, distance to river, distance to fault, fault density, distance to road, road density, land use, slope curvature, lithology, stream power index (SPI), and topographic wetness index (TWI). We identified 64 locations of landslides by field survey of which 70% were randomly employed for building and training the three MLAs while the remaining locations were used for validation. The area under the receiver operating characteristics (AUC) reached a value of 0.94 for the decision tree compared to 0.82 for the random forest, and 0.75 for support vector machines model. Thus, the decision tree model was most accurate in identifying the areas at risk for future landslides. The obtained results may inform geoscientists and those in decision-making roles for landslide management.https://www.mdpi.com/2072-4292/15/12/3112landslidesmachine learningrandom forestsupport vector machinedecision treeKamyaran–Sarvabad road |
| spellingShingle | Himan Shahabi Reza Ahmadi Mohsen Alizadeh Mazlan Hashim Nadhir Al-Ansari Ataollah Shirzadi Isabelle D. Wolf Effi Helmy Ariffin Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms Remote Sensing landslides machine learning random forest support vector machine decision tree Kamyaran–Sarvabad road |
| title | Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms |
| title_full | Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms |
| title_fullStr | Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms |
| title_full_unstemmed | Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms |
| title_short | Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms |
| title_sort | landslide susceptibility mapping in a mountainous area using machine learning algorithms |
| topic | landslides machine learning random forest support vector machine decision tree Kamyaran–Sarvabad road |
| url | https://www.mdpi.com/2072-4292/15/12/3112 |
| work_keys_str_mv | AT himanshahabi landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT rezaahmadi landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT mohsenalizadeh landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT mazlanhashim landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT nadhiralansari landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT ataollahshirzadi landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT isabelledwolf landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms AT effihelmyariffin landslidesusceptibilitymappinginamountainousareausingmachinelearningalgorithms |