An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling
Landslide susceptibility assessment is an effective non-engineering landslide prevention at the regional scale. This study aims to improve the accuracy of landslide susceptibility assessment by using an optimized statistical index (SI) method. A landslide inventory containing 493 historical landslid...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/20/10196 |
| _version_ | 1797475720703770624 |
|---|---|
| author | Cen Cheng Yang Yang Fengcheng Zhong Chao Song Yan Zhen |
| author_facet | Cen Cheng Yang Yang Fengcheng Zhong Chao Song Yan Zhen |
| author_sort | Cen Cheng |
| collection | DOAJ |
| description | Landslide susceptibility assessment is an effective non-engineering landslide prevention at the regional scale. This study aims to improve the accuracy of landslide susceptibility assessment by using an optimized statistical index (SI) method. A landslide inventory containing 493 historical landslides was established, and 20 initial influencing factors were selected for modeling. First, a combination of GeoDetector and recursive feature elimination was used to eliminate the redundant factors. Then, an optimization method for weights of SI was adopted based on Gaussian process regression (GPR). Finally, the predictive abilities of the original SI model, the SI model with optimized factors (GD-SI), and the SI model with optimized factors and weights (GD-GPR-SI) were compared and evaluated by the area under the receiver operating characteristic curve (AUC) on the testing datasets. The GD-GPR-SI model has the highest AUC value (0.943), and the GD-SI model (0.936) also has a higher value than the SI model (0.931). The results highlight the necessity of factor screening and weight optimization. The factor screening method used in this study can effectively eliminate factors that negatively affect the SI model. Furthermore, by optimizing the SI weights through GPR, more reasonable weights can be obtained for model performance improvement. |
| first_indexed | 2024-03-09T20:48:58Z |
| format | Article |
| id | doaj.art-d593132753984595b283a52e035faef3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:48:58Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d593132753984595b283a52e035faef32023-11-23T22:40:36ZengMDPI AGApplied Sciences2076-34172022-10-0112201019610.3390/app122010196An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility ModelingCen Cheng0Yang Yang1Fengcheng Zhong2Chao Song3Yan Zhen4State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, ChinaState Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, ChinaSpatial Information Technology and Big Data Mining Research Center, Southwest Petroleum University, Chengdu 610500, ChinaHEOA Group, West China School of Public Health and West China Fourth Hospital, Sichuan University, Chengdu 610044, ChinaState Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, ChinaLandslide susceptibility assessment is an effective non-engineering landslide prevention at the regional scale. This study aims to improve the accuracy of landslide susceptibility assessment by using an optimized statistical index (SI) method. A landslide inventory containing 493 historical landslides was established, and 20 initial influencing factors were selected for modeling. First, a combination of GeoDetector and recursive feature elimination was used to eliminate the redundant factors. Then, an optimization method for weights of SI was adopted based on Gaussian process regression (GPR). Finally, the predictive abilities of the original SI model, the SI model with optimized factors (GD-SI), and the SI model with optimized factors and weights (GD-GPR-SI) were compared and evaluated by the area under the receiver operating characteristic curve (AUC) on the testing datasets. The GD-GPR-SI model has the highest AUC value (0.943), and the GD-SI model (0.936) also has a higher value than the SI model (0.931). The results highlight the necessity of factor screening and weight optimization. The factor screening method used in this study can effectively eliminate factors that negatively affect the SI model. Furthermore, by optimizing the SI weights through GPR, more reasonable weights can be obtained for model performance improvement.https://www.mdpi.com/2076-3417/12/20/10196landslide susceptibilitystatistical indexGaussian process regressionGeoDetectorrecursive feature elimination |
| spellingShingle | Cen Cheng Yang Yang Fengcheng Zhong Chao Song Yan Zhen An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling Applied Sciences landslide susceptibility statistical index Gaussian process regression GeoDetector recursive feature elimination |
| title | An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling |
| title_full | An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling |
| title_fullStr | An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling |
| title_full_unstemmed | An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling |
| title_short | An Optimization of Statistical Index Method Based on Gaussian Process Regression and GeoDetector, for Higher Accurate Landslide Susceptibility Modeling |
| title_sort | optimization of statistical index method based on gaussian process regression and geodetector for higher accurate landslide susceptibility modeling |
| topic | landslide susceptibility statistical index Gaussian process regression GeoDetector recursive feature elimination |
| url | https://www.mdpi.com/2076-3417/12/20/10196 |
| work_keys_str_mv | AT cencheng anoptimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT yangyang anoptimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT fengchengzhong anoptimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT chaosong anoptimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT yanzhen anoptimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT cencheng optimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT yangyang optimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT fengchengzhong optimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT chaosong optimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling AT yanzhen optimizationofstatisticalindexmethodbasedongaussianprocessregressionandgeodetectorforhigheraccuratelandslidesusceptibilitymodeling |