Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township
Landslide susceptibility assessment forms the foundation for precise evaluation of landslide risk. To enhance the accuracy and robustness of landslide susceptibility mapping, a state-of-art machine learning algorithm named the extreme gradient boosting model (XGBoost) was introduced to this study. Y...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of The Chinese Journal of Geological Hazard and Control
2023-10-01
|
| Series: | Zhongguo dizhi zaihai yu fangzhi xuebao |
| Subjects: | |
| Online Access: | https://www.zgdzzhyfzxb.com/en/article/doi/10.16031/j.cnki.issn.1003-8035.202206020 |
| _version_ | 1797643653133369344 |
|---|---|
| author | Hongyang WU Chao ZHOU Xin LIANG Pengcheng YUAN Lanbing YU |
| author_facet | Hongyang WU Chao ZHOU Xin LIANG Pengcheng YUAN Lanbing YU |
| author_sort | Hongyang WU |
| collection | DOAJ |
| description | Landslide susceptibility assessment forms the foundation for precise evaluation of landslide risk. To enhance the accuracy and robustness of landslide susceptibility mapping, a state-of-art machine learning algorithm named the extreme gradient boosting model (XGBoost) was introduced to this study. Yanshan Town in Wanzhou district, Three Gorges reservoir, was chosen as a case study. Nine influencing factors, including engineering geological lithology and thickness of deposit layer, were selected to construct the landslide susceptibility evaluation index system. The relationship between landslide development and these indicators is quantitatively analyzed using the information value model. Subsequently, 70% of landslide samples were randomly assigned for training, while the remaining 30% were used for validation. The XGBoost model was then employed for landslide susceptibility mapping. The output were compared with those of the decision tree model (DT) and gradient boosting decision tree (GBDT) in terms of prediction accuracy and model stability. The findings revealed that distance to the Yangtze River, soil thickness, and lithology were the primary factors influencing landslide development. The XGBoost model demonstrated the highest average prediction accuracy (97.3%) in 100 repeated trials, surpassing the DT (91.3%) and GBDT models. Moreover, the XGBoost model exhibited superior robustness with a standard deviation and coefficient of variation of 0.01, lower than the other two models. It also achieved the highest accuracy (94.3%) and prediction accuracy (97.3%) in the validation process. The proposed XGBoost model serves as a reliable assessment method and yields optimal results in regional landslide susceptibility mapping. |
| first_indexed | 2024-03-11T14:18:01Z |
| format | Article |
| id | doaj.art-28ddf18154044962af3fd01f2eb3b419 |
| institution | Directory Open Access Journal |
| issn | 1003-8035 |
| language | zho |
| last_indexed | 2024-03-11T14:18:01Z |
| publishDate | 2023-10-01 |
| publisher | Editorial Office of The Chinese Journal of Geological Hazard and Control |
| record_format | Article |
| series | Zhongguo dizhi zaihai yu fangzhi xuebao |
| spelling | doaj.art-28ddf18154044962af3fd01f2eb3b4192023-11-01T02:11:37ZzhoEditorial Office of The Chinese Journal of Geological Hazard and ControlZhongguo dizhi zaihai yu fangzhi xuebao1003-80352023-10-0134514115210.16031/j.cnki.issn.1003-8035.202206020202206020Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan TownshipHongyang WU0Chao ZHOU1Xin LIANG2Pengcheng YUAN3Lanbing YU4School of Geography and Information Engineering, China University of Geosciences, Wuhan, Hubei 430078, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan, Hubei 430078, ChinaFaculty of Engineering, China University of Geosciences, Wuhan, Hubei 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan, Hubei 430078, ChinaFaculty of Engineering, China University of Geosciences, Wuhan, Hubei 430074, ChinaLandslide susceptibility assessment forms the foundation for precise evaluation of landslide risk. To enhance the accuracy and robustness of landslide susceptibility mapping, a state-of-art machine learning algorithm named the extreme gradient boosting model (XGBoost) was introduced to this study. Yanshan Town in Wanzhou district, Three Gorges reservoir, was chosen as a case study. Nine influencing factors, including engineering geological lithology and thickness of deposit layer, were selected to construct the landslide susceptibility evaluation index system. The relationship between landslide development and these indicators is quantitatively analyzed using the information value model. Subsequently, 70% of landslide samples were randomly assigned for training, while the remaining 30% were used for validation. The XGBoost model was then employed for landslide susceptibility mapping. The output were compared with those of the decision tree model (DT) and gradient boosting decision tree (GBDT) in terms of prediction accuracy and model stability. The findings revealed that distance to the Yangtze River, soil thickness, and lithology were the primary factors influencing landslide development. The XGBoost model demonstrated the highest average prediction accuracy (97.3%) in 100 repeated trials, surpassing the DT (91.3%) and GBDT models. Moreover, the XGBoost model exhibited superior robustness with a standard deviation and coefficient of variation of 0.01, lower than the other two models. It also achieved the highest accuracy (94.3%) and prediction accuracy (97.3%) in the validation process. The proposed XGBoost model serves as a reliable assessment method and yields optimal results in regional landslide susceptibility mapping.https://www.zgdzzhyfzxb.com/en/article/doi/10.16031/j.cnki.issn.1003-8035.202206020landslideslandslide susceptibility mappingextreme gradient boosting modelprediction accuracymodel robustness |
| spellingShingle | Hongyang WU Chao ZHOU Xin LIANG Pengcheng YUAN Lanbing YU Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township Zhongguo dizhi zaihai yu fangzhi xuebao landslides landslide susceptibility mapping extreme gradient boosting model prediction accuracy model robustness |
| title | Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township |
| title_full | Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township |
| title_fullStr | Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township |
| title_full_unstemmed | Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township |
| title_short | Assessment of landslide susceptibility mapping based on XGBoost model: A case study of Yanshan Township |
| title_sort | assessment of landslide susceptibility mapping based on xgboost model a case study of yanshan township |
| topic | landslides landslide susceptibility mapping extreme gradient boosting model prediction accuracy model robustness |
| url | https://www.zgdzzhyfzxb.com/en/article/doi/10.16031/j.cnki.issn.1003-8035.202206020 |
| work_keys_str_mv | AT hongyangwu assessmentoflandslidesusceptibilitymappingbasedonxgboostmodelacasestudyofyanshantownship AT chaozhou assessmentoflandslidesusceptibilitymappingbasedonxgboostmodelacasestudyofyanshantownship AT xinliang assessmentoflandslidesusceptibilitymappingbasedonxgboostmodelacasestudyofyanshantownship AT pengchengyuan assessmentoflandslidesusceptibilitymappingbasedonxgboostmodelacasestudyofyanshantownship AT lanbingyu assessmentoflandslidesusceptibilitymappingbasedonxgboostmodelacasestudyofyanshantownship |