Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor
Thaw slump susceptibility mapping (TSSM) of Qinghai–Tibet railway corridor (QTRC) is the prerequisite and basis for disaster assessment and prevention of permafrost projects. The objective of this article is to construct ensemble learning models based on single classifier models to genera...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10441819/ |
| _version_ | 1827126053215141888 |
|---|---|
| author | Yi He Tianbao Huo Binghai Gao Qing Zhu Long Jin Jian Chen Qing Zhang Jiapeng Tang |
| author_facet | Yi He Tianbao Huo Binghai Gao Qing Zhu Long Jin Jian Chen Qing Zhang Jiapeng Tang |
| author_sort | Yi He |
| collection | DOAJ |
| description | Thaw slump susceptibility mapping (TSSM) of Qinghai–Tibet railway corridor (QTRC) is the prerequisite and basis for disaster assessment and prevention of permafrost projects. The objective of this article is to construct ensemble learning models based on single classifier models to generate the TSSM of the QTRC, compare and verify the performance of the models, and further explore the relationship between the high susceptibility area and environmental factors of the QTRC. The collinearity analysis was carried out by selecting 14 thaw slump conditioning factors (TSCFs). We used the balance bagging method for sample optimization, and the dataset was divided into 70% training set and 30% verification set. Convolutional neural network, multilayer perceptron, support vector regression, random forest single classifiers were selected to construct blending and stacking ensemble learning models for the TSSM. The results showed that there was no collinearity among the 14 TSCFS. The comparison of model performance revealed that all models had good performance, but the constructed stacking and blending ensemble learning models had stable performance and high prediction accuracy for TSSM. The stacking ensemble learning model had the best effect, and the area under curve value of receiver operating characteristic curve reached 0.9607. It showed that the generated TSSM of QTRC based on stacking ensemble learning model had the highest reliability. The QTRC has local areas with high thaw slump susceptibility, mainly concentrated in the permafrost areas with high altitude, high slope, adjacent faults, sparse vegetation, ice and snow and the more cumulative precipitation. |
| first_indexed | 2024-03-07T14:05:05Z |
| format | Article |
| id | doaj.art-8c30fbb17f7447beb05cf4da5f91af8f |
| institution | Directory Open Access Journal |
| issn | 1939-1404 2151-1535 |
| language | English |
| last_indexed | 2025-03-20T15:06:29Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-8c30fbb17f7447beb05cf4da5f91af8f2024-09-05T23:00:29ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-01175443545910.1109/JSTARS.2024.336803910441819Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway CorridorYi He0https://orcid.org/0000-0003-4017-0488Tianbao Huo1https://orcid.org/0000-0001-7250-4927Binghai Gao2https://orcid.org/0009-0004-6015-3890Qing Zhu3https://orcid.org/0000-0002-0485-4965Long Jin4https://orcid.org/0009-0006-7046-1509Jian Chen5https://orcid.org/0009-0001-2797-7714Qing Zhang6https://orcid.org/0009-0005-0990-721XJiapeng Tang7https://orcid.org/0009-0003-3405-2888Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaSchool of Earth Science and Environmental Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaThaw slump susceptibility mapping (TSSM) of Qinghai–Tibet railway corridor (QTRC) is the prerequisite and basis for disaster assessment and prevention of permafrost projects. The objective of this article is to construct ensemble learning models based on single classifier models to generate the TSSM of the QTRC, compare and verify the performance of the models, and further explore the relationship between the high susceptibility area and environmental factors of the QTRC. The collinearity analysis was carried out by selecting 14 thaw slump conditioning factors (TSCFs). We used the balance bagging method for sample optimization, and the dataset was divided into 70% training set and 30% verification set. Convolutional neural network, multilayer perceptron, support vector regression, random forest single classifiers were selected to construct blending and stacking ensemble learning models for the TSSM. The results showed that there was no collinearity among the 14 TSCFS. The comparison of model performance revealed that all models had good performance, but the constructed stacking and blending ensemble learning models had stable performance and high prediction accuracy for TSSM. The stacking ensemble learning model had the best effect, and the area under curve value of receiver operating characteristic curve reached 0.9607. It showed that the generated TSSM of QTRC based on stacking ensemble learning model had the highest reliability. The QTRC has local areas with high thaw slump susceptibility, mainly concentrated in the permafrost areas with high altitude, high slope, adjacent faults, sparse vegetation, ice and snow and the more cumulative precipitation.https://ieeexplore.ieee.org/document/10441819/Ensemble learningQinghai–Tibet railwaysample optimizationthaw slump susceptibility mapping (TSSM) |
| spellingShingle | Yi He Tianbao Huo Binghai Gao Qing Zhu Long Jin Jian Chen Qing Zhang Jiapeng Tang Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Ensemble learning Qinghai–Tibet railway sample optimization thaw slump susceptibility mapping (TSSM) |
| title | Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor |
| title_full | Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor |
| title_fullStr | Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor |
| title_full_unstemmed | Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor |
| title_short | Thaw Slump Susceptibility Mapping Based on Sample Optimization and Ensemble Learning Techniques in Qinghai-Tibet Railway Corridor |
| title_sort | thaw slump susceptibility mapping based on sample optimization and ensemble learning techniques in qinghai tibet railway corridor |
| topic | Ensemble learning Qinghai–Tibet railway sample optimization thaw slump susceptibility mapping (TSSM) |
| url | https://ieeexplore.ieee.org/document/10441819/ |
| work_keys_str_mv | AT yihe thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT tianbaohuo thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT binghaigao thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT qingzhu thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT longjin thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT jianchen thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT qingzhang thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor AT jiapengtang thawslumpsusceptibilitymappingbasedonsampleoptimizationandensemblelearningtechniquesinqinghaitibetrailwaycorridor |