GIS-based landslide susceptibility modeling using data mining techniques
Introduction: Landslide is one of the most widespread geohazards around the world. Therefore, it is necessary and meaningful to map regional landslide susceptibility for landslide mitigation. In this research, landslide susceptibility maps were produced by four models, namely, certainty factors (CF)...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2023.1187384/full |
| _version_ | 1797796698855047168 |
|---|---|
| author | Liheng Xia Liheng Xia Liheng Xia Jianglong Shen Jianglong Shen Jianglong Shen Tingyu Zhang Tingyu Zhang Tingyu Zhang Guangpu Dang Tao Wang |
| author_facet | Liheng Xia Liheng Xia Liheng Xia Jianglong Shen Jianglong Shen Jianglong Shen Tingyu Zhang Tingyu Zhang Tingyu Zhang Guangpu Dang Tao Wang |
| author_sort | Liheng Xia |
| collection | DOAJ |
| description | Introduction: Landslide is one of the most widespread geohazards around the world. Therefore, it is necessary and meaningful to map regional landslide susceptibility for landslide mitigation. In this research, landslide susceptibility maps were produced by four models, namely, certainty factors (CF), naive Bayes (NB), J48 decision tree (J48), and multilayer perceptron (MLP) models.Methods: In the first step, 328 landslides were identified via historical data, interpretation of remote sensing images, and field investigation, and they were divided into two subsets that were assigned different uses: 70% subset for training and 30% subset for validating. Then, twelve conditioning factors were employed, namely, altitude, slope angle, slope aspect, plan curvature, profile curvature, TWI, NDVI, distance to rivers, distance to roads, land use, soil, and lithology. Later, the importance of each conditioning factor was analyzed by average merit (AM) values, and the relationship between landslide occurrence and various factors was evaluated using the certainty factor (CF) approach. In the next step, the landslide susceptibility maps were produced based on four models, and the effect of the four models were quantitatively compared by receiver operating characteristic (ROC) curves, area under curve (AUC) values, and non-parametric tests.Results: The results demonstrated that all the four models can reasonably assess landslide susceptibility. Of these four models, the CF model has the best predictive performance for the training (AUC=0.901) and validating data (AUC=0.892).Discussion: The proposed approach is an innovative method that may also help other scientists to develop landslide susceptibility maps in other areas and that could be used for geo-environmental problems besides natural hazard assessments. |
| first_indexed | 2024-03-13T03:36:58Z |
| format | Article |
| id | doaj.art-f38c18c6896342bcb87e27a9a63572f4 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-03-13T03:36:58Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-f38c18c6896342bcb87e27a9a63572f42023-06-23T17:37:01ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-06-011110.3389/feart.2023.11873841187384GIS-based landslide susceptibility modeling using data mining techniquesLiheng Xia0Liheng Xia1Liheng Xia2Jianglong Shen3Jianglong Shen4Jianglong Shen5Tingyu Zhang6Tingyu Zhang7Tingyu Zhang8Guangpu Dang9Tao Wang10Key Laboratory of Degraded and Unused Land Consolidation Engineering, Ministry of Natural Resources, Xi’an, ChinaShaanxi Provincial Land Consolidation Engineering Technology Research Center, Xi’an, ChinaLand Engineering Technology Innovation Center, Ministry of Natural Resources, Xi’an, ChinaKey Laboratory of Degraded and Unused Land Consolidation Engineering, Ministry of Natural Resources, Xi’an, ChinaShaanxi Provincial Land Consolidation Engineering Technology Research Center, Xi’an, ChinaLand Engineering Technology Innovation Center, Ministry of Natural Resources, Xi’an, ChinaKey Laboratory of Degraded and Unused Land Consolidation Engineering, Ministry of Natural Resources, Xi’an, ChinaShaanxi Provincial Land Consolidation Engineering Technology Research Center, Xi’an, ChinaLand Engineering Technology Innovation Center, Ministry of Natural Resources, Xi’an, ChinaShaanxi Provincial Land Engineering Construction Group, Land Survey Planning and Design Institute, Xi’an, ChinaShaanxi Provincial Land Engineering Construction Group, Land Survey Planning and Design Institute, Xi’an, ChinaIntroduction: Landslide is one of the most widespread geohazards around the world. Therefore, it is necessary and meaningful to map regional landslide susceptibility for landslide mitigation. In this research, landslide susceptibility maps were produced by four models, namely, certainty factors (CF), naive Bayes (NB), J48 decision tree (J48), and multilayer perceptron (MLP) models.Methods: In the first step, 328 landslides were identified via historical data, interpretation of remote sensing images, and field investigation, and they were divided into two subsets that were assigned different uses: 70% subset for training and 30% subset for validating. Then, twelve conditioning factors were employed, namely, altitude, slope angle, slope aspect, plan curvature, profile curvature, TWI, NDVI, distance to rivers, distance to roads, land use, soil, and lithology. Later, the importance of each conditioning factor was analyzed by average merit (AM) values, and the relationship between landslide occurrence and various factors was evaluated using the certainty factor (CF) approach. In the next step, the landslide susceptibility maps were produced based on four models, and the effect of the four models were quantitatively compared by receiver operating characteristic (ROC) curves, area under curve (AUC) values, and non-parametric tests.Results: The results demonstrated that all the four models can reasonably assess landslide susceptibility. Of these four models, the CF model has the best predictive performance for the training (AUC=0.901) and validating data (AUC=0.892).Discussion: The proposed approach is an innovative method that may also help other scientists to develop landslide susceptibility maps in other areas and that could be used for geo-environmental problems besides natural hazard assessments.https://www.frontiersin.org/articles/10.3389/feart.2023.1187384/fulllandslide susceptibilitynaive bayes classifierJ48 decision treemultilayer perceptronGIS |
| spellingShingle | Liheng Xia Liheng Xia Liheng Xia Jianglong Shen Jianglong Shen Jianglong Shen Tingyu Zhang Tingyu Zhang Tingyu Zhang Guangpu Dang Tao Wang GIS-based landslide susceptibility modeling using data mining techniques Frontiers in Earth Science landslide susceptibility naive bayes classifier J48 decision tree multilayer perceptron GIS |
| title | GIS-based landslide susceptibility modeling using data mining techniques |
| title_full | GIS-based landslide susceptibility modeling using data mining techniques |
| title_fullStr | GIS-based landslide susceptibility modeling using data mining techniques |
| title_full_unstemmed | GIS-based landslide susceptibility modeling using data mining techniques |
| title_short | GIS-based landslide susceptibility modeling using data mining techniques |
| title_sort | gis based landslide susceptibility modeling using data mining techniques |
| topic | landslide susceptibility naive bayes classifier J48 decision tree multilayer perceptron GIS |
| url | https://www.frontiersin.org/articles/10.3389/feart.2023.1187384/full |
| work_keys_str_mv | AT lihengxia gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT lihengxia gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT lihengxia gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT jianglongshen gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT jianglongshen gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT jianglongshen gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT tingyuzhang gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT tingyuzhang gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT tingyuzhang gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT guangpudang gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques AT taowang gisbasedlandslidesusceptibilitymodelingusingdataminingtechniques |