FR-weighted GeoDetector for landslide susceptibility and driving factors analysis
AbstractLandslide susceptibility analysis is an essential tool for landslide hazard management. Correlation analysis of the driving factors before landslide susceptibility analysis is crucial to obtain more accurate results and higher computational efficiency. This article presents an FR-weighted Ge...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Geomatics, Natural Hazards & Risk |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19475705.2023.2205001 |
| _version_ | 1797389189599199232 |
|---|---|
| author | Linya Peng Yangjie Sun Zhao Zhan Wenzhong Shi Min Zhang |
| author_facet | Linya Peng Yangjie Sun Zhao Zhan Wenzhong Shi Min Zhang |
| author_sort | Linya Peng |
| collection | DOAJ |
| description | AbstractLandslide susceptibility analysis is an essential tool for landslide hazard management. Correlation analysis of the driving factors before landslide susceptibility analysis is crucial to obtain more accurate results and higher computational efficiency. This article presents an FR-weighted GeoDetector, which can, at different gridding scales, stably screen out the driving factors most relevant to historical landslides in the study area compared to the performance of the original GeoDetector. The correlation analysis result shows that the most relevant seven conditioning factors to historical landslides in the study area are: lithology, distance to road, elevation, slope, STI, SPI, and distance to faults. Four machine learning models (logistic regression [LR], random forest [RF], artificial neural network [ANN], and Xgboost) are implemented for landslide susceptibility analysis, demonstrating that such models can achieve higher accuracy with features filtered by the FR-weighted GeoDetector than with all features. The Xgboost models trained on seven and 12 features were used to generate landslide susceptibility maps. The overlay with historical landslides showed that the models trained on seven features generated a more reasonable landslide susceptibility map, proving that selecting crucial landslide conditioning factors is a better solution than using a full range of landslide conditioning factors. |
| first_indexed | 2024-03-08T22:52:15Z |
| format | Article |
| id | doaj.art-1d5ad8dc119e499dab74c7cd933ca255 |
| institution | Directory Open Access Journal |
| issn | 1947-5705 1947-5713 |
| language | English |
| last_indexed | 2024-03-08T22:52:15Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geomatics, Natural Hazards & Risk |
| spelling | doaj.art-1d5ad8dc119e499dab74c7cd933ca2552023-12-16T08:49:46ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132023-12-0114110.1080/19475705.2023.2205001FR-weighted GeoDetector for landslide susceptibility and driving factors analysisLinya Peng0Yangjie Sun1Zhao Zhan2Wenzhong Shi3Min Zhang4The School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, PR ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ROC;The School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, PR ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ROC;Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, ROC;AbstractLandslide susceptibility analysis is an essential tool for landslide hazard management. Correlation analysis of the driving factors before landslide susceptibility analysis is crucial to obtain more accurate results and higher computational efficiency. This article presents an FR-weighted GeoDetector, which can, at different gridding scales, stably screen out the driving factors most relevant to historical landslides in the study area compared to the performance of the original GeoDetector. The correlation analysis result shows that the most relevant seven conditioning factors to historical landslides in the study area are: lithology, distance to road, elevation, slope, STI, SPI, and distance to faults. Four machine learning models (logistic regression [LR], random forest [RF], artificial neural network [ANN], and Xgboost) are implemented for landslide susceptibility analysis, demonstrating that such models can achieve higher accuracy with features filtered by the FR-weighted GeoDetector than with all features. The Xgboost models trained on seven and 12 features were used to generate landslide susceptibility maps. The overlay with historical landslides showed that the models trained on seven features generated a more reasonable landslide susceptibility map, proving that selecting crucial landslide conditioning factors is a better solution than using a full range of landslide conditioning factors.https://www.tandfonline.com/doi/10.1080/19475705.2023.2205001Landslide susceptibilityGeoDetectorcorrelation analysisdriving factors |
| spellingShingle | Linya Peng Yangjie Sun Zhao Zhan Wenzhong Shi Min Zhang FR-weighted GeoDetector for landslide susceptibility and driving factors analysis Geomatics, Natural Hazards & Risk Landslide susceptibility GeoDetector correlation analysis driving factors |
| title | FR-weighted GeoDetector for landslide susceptibility and driving factors analysis |
| title_full | FR-weighted GeoDetector for landslide susceptibility and driving factors analysis |
| title_fullStr | FR-weighted GeoDetector for landslide susceptibility and driving factors analysis |
| title_full_unstemmed | FR-weighted GeoDetector for landslide susceptibility and driving factors analysis |
| title_short | FR-weighted GeoDetector for landslide susceptibility and driving factors analysis |
| title_sort | fr weighted geodetector for landslide susceptibility and driving factors analysis |
| topic | Landslide susceptibility GeoDetector correlation analysis driving factors |
| url | https://www.tandfonline.com/doi/10.1080/19475705.2023.2205001 |
| work_keys_str_mv | AT linyapeng frweightedgeodetectorforlandslidesusceptibilityanddrivingfactorsanalysis AT yangjiesun frweightedgeodetectorforlandslidesusceptibilityanddrivingfactorsanalysis AT zhaozhan frweightedgeodetectorforlandslidesusceptibilityanddrivingfactorsanalysis AT wenzhongshi frweightedgeodetectorforlandslidesusceptibilityanddrivingfactorsanalysis AT minzhang frweightedgeodetectorforlandslidesusceptibilityanddrivingfactorsanalysis |