Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods
Landslides are frequent natural hazards in mountainous regions, and harshly upset people's lives and livelihoods. In the present study, we have carried out an analysis of seven GIS-based machine-learning techniques; and asses their performance for landslide susceptibility mapping (LSM) in the B...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-05-01
|
| Series: | Geosystems and Geoenvironment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772883824000037 |
| _version_ | 1827279037669572608 |
|---|---|
| author | Suresh Chand Rai Vijendra Kumar Pandey Kaushal Kumar Sharma Sanjeev Sharma |
| author_facet | Suresh Chand Rai Vijendra Kumar Pandey Kaushal Kumar Sharma Sanjeev Sharma |
| author_sort | Suresh Chand Rai |
| collection | DOAJ |
| description | Landslides are frequent natural hazards in mountainous regions, and harshly upset people's lives and livelihoods. In the present study, we have carried out an analysis of seven GIS-based machine-learning techniques; and asses their performance for landslide susceptibility mapping (LSM) in the Bhilangana Basin, Garhwal Himalaya. A landslide inventory consisting of 423 polygons was prepared using repeated field investigations, and multi-dated satellite images for the periods between 2000 and 2022. The landslide dataset was classified into two groups: training (70%) and test dataset (30%), and 12 predictive variables were used for the LSM. The methods used to produce LSM are boosted regression tree (BRT), Fisher discriminant analysis (FDA), generalized linear model (GLM), multivariate adaptive regression splines (MARS), model-architect analysis (MDA), random forest (RF) and support vector machine (SVM). The sensitivity and performance of these models to predict landslide susceptible areas were carried out using the area under the curve (AUC) method. The RF model (AUC = 0.988) has given the highest precision indicating the best performance. Though MARS (0.974), SVM (0.965) and MDA (0.952) models have also performed adequately for the LSM (all have AUC values above 0.95), however, it is recommended that the RF model is highly suitable for LSM in the mountainous region. |
| first_indexed | 2024-03-08T10:28:17Z |
| format | Article |
| id | doaj.art-20107e8eaf0445f1a96a23bca5fbfd47 |
| institution | Directory Open Access Journal |
| issn | 2772-8838 |
| language | English |
| last_indexed | 2024-04-24T08:11:17Z |
| publishDate | 2024-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Geosystems and Geoenvironment |
| spelling | doaj.art-20107e8eaf0445f1a96a23bca5fbfd472024-04-17T04:50:24ZengElsevierGeosystems and Geoenvironment2772-88382024-05-0132100253Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methodsSuresh Chand Rai0Vijendra Kumar Pandey1Kaushal Kumar Sharma2Sanjeev Sharma3Department of Geography, Delhi School of Economics, University of Delhi, Delhi 110007, IndiaDepartment of Geography, Kirori Mal College, University of Delhi, Delhi 110007, India; Corresponding author.CSRD, School of Social Sciences, Jawaharlal Nehru University, New Delhi 110067, IndiaCSRD, School of Social Sciences, Jawaharlal Nehru University, New Delhi 110067, IndiaLandslides are frequent natural hazards in mountainous regions, and harshly upset people's lives and livelihoods. In the present study, we have carried out an analysis of seven GIS-based machine-learning techniques; and asses their performance for landslide susceptibility mapping (LSM) in the Bhilangana Basin, Garhwal Himalaya. A landslide inventory consisting of 423 polygons was prepared using repeated field investigations, and multi-dated satellite images for the periods between 2000 and 2022. The landslide dataset was classified into two groups: training (70%) and test dataset (30%), and 12 predictive variables were used for the LSM. The methods used to produce LSM are boosted regression tree (BRT), Fisher discriminant analysis (FDA), generalized linear model (GLM), multivariate adaptive regression splines (MARS), model-architect analysis (MDA), random forest (RF) and support vector machine (SVM). The sensitivity and performance of these models to predict landslide susceptible areas were carried out using the area under the curve (AUC) method. The RF model (AUC = 0.988) has given the highest precision indicating the best performance. Though MARS (0.974), SVM (0.965) and MDA (0.952) models have also performed adequately for the LSM (all have AUC values above 0.95), however, it is recommended that the RF model is highly suitable for LSM in the mountainous region.http://www.sciencedirect.com/science/article/pii/S2772883824000037Landslide inventoryMachine learning techniquesGeo-environmental hazardsCentral HimalayaTehri GarhwalUttarakhand |
| spellingShingle | Suresh Chand Rai Vijendra Kumar Pandey Kaushal Kumar Sharma Sanjeev Sharma Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods Geosystems and Geoenvironment Landslide inventory Machine learning techniques Geo-environmental hazards Central Himalaya Tehri Garhwal Uttarakhand |
| title | Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods |
| title_full | Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods |
| title_fullStr | Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods |
| title_full_unstemmed | Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods |
| title_short | Landslide susceptibility analysis in the Bhilangana Basin (India) using GIS-based machine learning methods |
| title_sort | landslide susceptibility analysis in the bhilangana basin india using gis based machine learning methods |
| topic | Landslide inventory Machine learning techniques Geo-environmental hazards Central Himalaya Tehri Garhwal Uttarakhand |
| url | http://www.sciencedirect.com/science/article/pii/S2772883824000037 |
| work_keys_str_mv | AT sureshchandrai landslidesusceptibilityanalysisinthebhilanganabasinindiausinggisbasedmachinelearningmethods AT vijendrakumarpandey landslidesusceptibilityanalysisinthebhilanganabasinindiausinggisbasedmachinelearningmethods AT kaushalkumarsharma landslidesusceptibilityanalysisinthebhilanganabasinindiausinggisbasedmachinelearningmethods AT sanjeevsharma landslidesusceptibilityanalysisinthebhilanganabasinindiausinggisbasedmachinelearningmethods |