A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China
The improvement of landslide susceptibility assessment is a long-standing problem in hazard mitigation work, wherein previous studies have proposed various training models. However, the ratio of positive to negative samples and the selection of non-landslide samples have been shown to significantly...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Geomatics, Natural Hazards & Risk |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19475705.2024.2354507 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846126399573721088 |
|---|---|
| author | Nan Jiang Yange Li Zheng Han Jiaming Yang Bangjie Fu Jiaying Li Changli Li |
| author_facet | Nan Jiang Yange Li Zheng Han Jiaming Yang Bangjie Fu Jiaying Li Changli Li |
| author_sort | Nan Jiang |
| collection | DOAJ |
| description | The improvement of landslide susceptibility assessment is a long-standing problem in hazard mitigation work, wherein previous studies have proposed various training models. However, the ratio of positive to negative samples and the selection of non-landslide samples have been shown to significantly influence results. These research directions have traditionally been focal points, while datasets are often overlooked, serving merely as auxiliary tools to support the validation process. Hence, this study proposes an approach to enhance datasets through the introduction of the side-sampling method. This technique focuses on individual research cells, conducting feature sampling training on fixed regions of length M, thereby enabling more precise identification of geographical clustering characteristics. Using evaluation metrics such as accuracy, precision, recall, F1 score, and ROC curve, this study conducts a comparative analysis between the side-sampling method and traditional sampling methods, using three distinct railway lines in China as the study areas. Results show substantial improvements beyond several exceptions: accuracy (+7.68%), precision (+7.19%), recall (+13.48%), F1 score (+9.92%), and ROC (+6.22%). The results demonstrate a significant overall improvement in the performance of the trained models based on the side-sampling method, providing a positive insight into mitigating landslide hazards along railways from the dataset perspective. |
| format | Article |
| id | doaj-art-0e4dcb00ee60416f858ba1d076861a5e |
| institution | Kabale University |
| issn | 1947-5705 1947-5713 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geomatics, Natural Hazards & Risk |
| spelling | doaj-art-0e4dcb00ee60416f858ba1d076861a5e2024-12-12T18:11:18ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132024-12-0115110.1080/19475705.2024.2354507A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in ChinaNan Jiang0Yange Li1Zheng Han2Jiaming Yang3Bangjie Fu4Jiaying Li5Changli Li6School of Civil Engineering, Central South University, Changsha, ChinaSchool of Civil Engineering, Central South University, Changsha, ChinaSchool of Civil Engineering, Central South University, Changsha, ChinaSchool of Civil Engineering, Central South University, Changsha, ChinaSchool of Civil Engineering, Central South University, Changsha, ChinaSchool of Civil Engineering, Xiangtan University, Xiangtan, ChinaSchool of Civil Engineering, Central South University, Changsha, ChinaThe improvement of landslide susceptibility assessment is a long-standing problem in hazard mitigation work, wherein previous studies have proposed various training models. However, the ratio of positive to negative samples and the selection of non-landslide samples have been shown to significantly influence results. These research directions have traditionally been focal points, while datasets are often overlooked, serving merely as auxiliary tools to support the validation process. Hence, this study proposes an approach to enhance datasets through the introduction of the side-sampling method. This technique focuses on individual research cells, conducting feature sampling training on fixed regions of length M, thereby enabling more precise identification of geographical clustering characteristics. Using evaluation metrics such as accuracy, precision, recall, F1 score, and ROC curve, this study conducts a comparative analysis between the side-sampling method and traditional sampling methods, using three distinct railway lines in China as the study areas. Results show substantial improvements beyond several exceptions: accuracy (+7.68%), precision (+7.19%), recall (+13.48%), F1 score (+9.92%), and ROC (+6.22%). The results demonstrate a significant overall improvement in the performance of the trained models based on the side-sampling method, providing a positive insight into mitigating landslide hazards along railways from the dataset perspective.https://www.tandfonline.com/doi/10.1080/19475705.2024.2354507Landslidesusceptibility assessmentrailway hazardside-samplingLinformer model |
| spellingShingle | Nan Jiang Yange Li Zheng Han Jiaming Yang Bangjie Fu Jiaying Li Changli Li A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China Geomatics, Natural Hazards & Risk Landslide susceptibility assessment railway hazard side-sampling Linformer model |
| title | A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China |
| title_full | A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China |
| title_fullStr | A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China |
| title_full_unstemmed | A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China |
| title_short | A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China |
| title_sort | side sampling based linformer model for landslide susceptibility assessment a case study of the railways in china |
| topic | Landslide susceptibility assessment railway hazard side-sampling Linformer model |
| url | https://www.tandfonline.com/doi/10.1080/19475705.2024.2354507 |
| work_keys_str_mv | AT nanjiang asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT yangeli asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT zhenghan asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT jiamingyang asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT bangjiefu asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT jiayingli asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT changlili asidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT nanjiang sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT yangeli sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT zhenghan sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT jiamingyang sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT bangjiefu sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT jiayingli sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina AT changlili sidesamplingbasedlinformermodelforlandslidesusceptibilityassessmentacasestudyoftherailwaysinchina |