Handling imbalanced samples in landslide susceptibility evaluation
In landslide susceptibility assessment, different approaches to handling sample imbalance can introduce significant uncertainty in evaluation outcomes. To address this issue, this study focused on the Changdu area of eastern Tibet and constructed the landslide susceptibility evaluation model using a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Hydrogeology & Engineering Geology
2024-11-01
|
| Series: | Shuiwen dizhi gongcheng dizhi |
| Subjects: | |
| Online Access: | https://www.swdzgcdz.com/en/article/doi/10.16030/j.cnki.issn.1000-3665.202307002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524938859610112 |
|---|---|
| author | You TIAN Bo GAO Hong YIN Yuanling LI Jiajia ZHANG Long CHEN Hongliang LI |
| author_facet | You TIAN Bo GAO Hong YIN Yuanling LI Jiajia ZHANG Long CHEN Hongliang LI |
| author_sort | You TIAN |
| collection | DOAJ |
| description | In landslide susceptibility assessment, different approaches to handling sample imbalance can introduce significant uncertainty in evaluation outcomes. To address this issue, this study focused on the Changdu area of eastern Tibet and constructed the landslide susceptibility evaluation model using a dataset with imbalanced landslide and non-landslide samples. Three disposal schemes were applied: no treatment, downsampling, and SMOTE oversampling. The logistic regression method was used to construct the landslide susceptibility evaluation model. Based on ROC curve, accuracy, precision, recall, missed detection rate, and other evaluation indicators, the comprehensive evaluation index of F1′ score was used to verify the accuracy of model classification. The results show that the modeling effect of landslide susceptibility obtained by data processing into equilibrium data (downsampling/oversampling) is greatly improved compared with that obtained without processing data. Specifically, the value of the F1′score of the comprehensive index was increased by 53.17%. In the two schemes for processing data (downsampling and oversampling), the oversampling method increased the value of the composite index F1′ score by 16.30% compared with the downsampling method, indicating that the oversampling method has effectiveness in handling unbalanced data. This study can provide basic information for processing of data sets before landslide prediction and geological disaster prediction, and provide theoretical and technical support for further improving regional disaster prevention and mitigation. |
| format | Article |
| id | doaj-art-ebf38d8676b04ff4bc51812f09544a51 |
| institution | Kabale University |
| issn | 1000-3665 |
| language | zho |
| publishDate | 2024-11-01 |
| publisher | Editorial Office of Hydrogeology & Engineering Geology |
| record_format | Article |
| series | Shuiwen dizhi gongcheng dizhi |
| spelling | doaj-art-ebf38d8676b04ff4bc51812f09544a512025-01-18T03:53:12ZzhoEditorial Office of Hydrogeology & Engineering GeologyShuiwen dizhi gongcheng dizhi1000-36652024-11-0151617118110.16030/j.cnki.issn.1000-3665.202307002202307002Handling imbalanced samples in landslide susceptibility evaluationYou TIAN0Bo GAO1Hong YIN2Yuanling LI3Jiajia ZHANG4Long CHEN5Hongliang LI6Institute of Exploration Technology, Chinese Academy of Geological Sciences, Chengdu, Sichuan 611734, ChinaInstitute of Exploration Technology, Chinese Academy of Geological Sciences, Chengdu, Sichuan 611734, ChinaSichuan Province Engineering Technology Research Center of Geohazard Prevention, Chengdu, Sichuan 610081, ChinaInstitute of Exploration Technology, Chinese Academy of Geological Sciences, Chengdu, Sichuan 611734, ChinaInstitute of Exploration Technology, Chinese Academy of Geological Sciences, Chengdu, Sichuan 611734, ChinaInstitute of Exploration Technology, Chinese Academy of Geological Sciences, Chengdu, Sichuan 611734, ChinaInstitute of Exploration Technology, Chinese Academy of Geological Sciences, Chengdu, Sichuan 611734, ChinaIn landslide susceptibility assessment, different approaches to handling sample imbalance can introduce significant uncertainty in evaluation outcomes. To address this issue, this study focused on the Changdu area of eastern Tibet and constructed the landslide susceptibility evaluation model using a dataset with imbalanced landslide and non-landslide samples. Three disposal schemes were applied: no treatment, downsampling, and SMOTE oversampling. The logistic regression method was used to construct the landslide susceptibility evaluation model. Based on ROC curve, accuracy, precision, recall, missed detection rate, and other evaluation indicators, the comprehensive evaluation index of F1′ score was used to verify the accuracy of model classification. The results show that the modeling effect of landslide susceptibility obtained by data processing into equilibrium data (downsampling/oversampling) is greatly improved compared with that obtained without processing data. Specifically, the value of the F1′score of the comprehensive index was increased by 53.17%. In the two schemes for processing data (downsampling and oversampling), the oversampling method increased the value of the composite index F1′ score by 16.30% compared with the downsampling method, indicating that the oversampling method has effectiveness in handling unbalanced data. This study can provide basic information for processing of data sets before landslide prediction and geological disaster prediction, and provide theoretical and technical support for further improving regional disaster prevention and mitigation.https://www.swdzgcdz.com/en/article/doi/10.16030/j.cnki.issn.1000-3665.202307002landslide susceptibilitysmoteevaluation modelchangduunbalanced data |
| spellingShingle | You TIAN Bo GAO Hong YIN Yuanling LI Jiajia ZHANG Long CHEN Hongliang LI Handling imbalanced samples in landslide susceptibility evaluation Shuiwen dizhi gongcheng dizhi landslide susceptibility smote evaluation model changdu unbalanced data |
| title | Handling imbalanced samples in landslide susceptibility evaluation |
| title_full | Handling imbalanced samples in landslide susceptibility evaluation |
| title_fullStr | Handling imbalanced samples in landslide susceptibility evaluation |
| title_full_unstemmed | Handling imbalanced samples in landslide susceptibility evaluation |
| title_short | Handling imbalanced samples in landslide susceptibility evaluation |
| title_sort | handling imbalanced samples in landslide susceptibility evaluation |
| topic | landslide susceptibility smote evaluation model changdu unbalanced data |
| url | https://www.swdzgcdz.com/en/article/doi/10.16030/j.cnki.issn.1000-3665.202307002 |
| work_keys_str_mv | AT youtian handlingimbalancedsamplesinlandslidesusceptibilityevaluation AT bogao handlingimbalancedsamplesinlandslidesusceptibilityevaluation AT hongyin handlingimbalancedsamplesinlandslidesusceptibilityevaluation AT yuanlingli handlingimbalancedsamplesinlandslidesusceptibilityevaluation AT jiajiazhang handlingimbalancedsamplesinlandslidesusceptibilityevaluation AT longchen handlingimbalancedsamplesinlandslidesusceptibilityevaluation AT hongliangli handlingimbalancedsamplesinlandslidesusceptibilityevaluation |