Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost
Landslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly and accurately is the basis of landslide disaster prevention. Fengjie County, Chongqing, China, is a typical landslide-prone area in the Three...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/15/3901 |
| _version_ | 1797586029036699648 |
|---|---|
| author | Na Lin Di Zhang Shanshan Feng Kai Ding Libing Tan Bin Wang Tao Chen Weile Li Xiaoai Dai Jianping Pan Feifei Tang |
| author_facet | Na Lin Di Zhang Shanshan Feng Kai Ding Libing Tan Bin Wang Tao Chen Weile Li Xiaoai Dai Jianping Pan Feifei Tang |
| author_sort | Na Lin |
| collection | DOAJ |
| description | Landslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly and accurately is the basis of landslide disaster prevention. Fengjie County, Chongqing, China, is a typical landslide-prone area in the Three Gorges Reservoir Area. In this study, we newly integrate Shapley Additive Explanation (SHAP) and Optuna (OPT) hyperparameter tuning into four basic machine learning algorithms: Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Additive Boosting (AdaBoost). We construct four new models (SHAP-OPT-GBDT, SHAP-OPT-XGBoost, SHAP-OPT-LightGBM, and SHAP-OPT-AdaBoost) and apply the four new models to landslide extraction for the first time. Firstly, high-resolution remote sensing images were preprocessed, landslide and non-landslide samples were constructed, and an initial feature set with 48 features was built. Secondly, SHAP was used to select features with significant contributions, and the important features were selected. Finally, Optuna, the Bayesian optimization technique, was utilized to automatically select the basic models’ best hyperparameters. The experimental results show that the accuracy (ACC) of these four SHAP-OPT models was above 92% and the training time was less than 1.3 s using mediocre computational hardware. Furthermore, SHAP-OPT-XGBoost achieved the highest accuracy (96.26%). Landslide distribution information in Fengjie County from 2013 to 2020 can be extracted by SHAP-OPT-XGBoost accurately and quickly. |
| first_indexed | 2024-03-11T00:17:29Z |
| format | Article |
| id | doaj.art-6fb7db89e6784bad8c892c59205da868 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:17:29Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6fb7db89e6784bad8c892c59205da8682023-11-18T23:32:24ZengMDPI AGRemote Sensing2072-42922023-08-011515390110.3390/rs15153901Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoostNa Lin0Di Zhang1Shanshan Feng2Kai Ding3Libing Tan4Bin Wang5Tao Chen6Weile Li7Xiaoai Dai8Jianping Pan9Feifei Tang10School of Smart City, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Smart City, Chongqing Jiaotong University, Chongqing 400074, ChinaQinghai Transportation Planning and Design Institute Co., Ltd., Xining 810000, ChinaSchool of Smart City, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Smart City, Chongqing Jiaotong University, Chongqing 400074, ChinaChongqing Geomatics and Remote Sensing Center, Chongqing 401125, ChinaSchool of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, ChinaCollege of Earth Science, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Smart City, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Smart City, Chongqing Jiaotong University, Chongqing 400074, ChinaLandslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly and accurately is the basis of landslide disaster prevention. Fengjie County, Chongqing, China, is a typical landslide-prone area in the Three Gorges Reservoir Area. In this study, we newly integrate Shapley Additive Explanation (SHAP) and Optuna (OPT) hyperparameter tuning into four basic machine learning algorithms: Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Additive Boosting (AdaBoost). We construct four new models (SHAP-OPT-GBDT, SHAP-OPT-XGBoost, SHAP-OPT-LightGBM, and SHAP-OPT-AdaBoost) and apply the four new models to landslide extraction for the first time. Firstly, high-resolution remote sensing images were preprocessed, landslide and non-landslide samples were constructed, and an initial feature set with 48 features was built. Secondly, SHAP was used to select features with significant contributions, and the important features were selected. Finally, Optuna, the Bayesian optimization technique, was utilized to automatically select the basic models’ best hyperparameters. The experimental results show that the accuracy (ACC) of these four SHAP-OPT models was above 92% and the training time was less than 1.3 s using mediocre computational hardware. Furthermore, SHAP-OPT-XGBoost achieved the highest accuracy (96.26%). Landslide distribution information in Fengjie County from 2013 to 2020 can be extracted by SHAP-OPT-XGBoost accurately and quickly.https://www.mdpi.com/2072-4292/15/15/3901landslide extractionXGBoosthigh-resolution remote sensingSHAPOptuna |
| spellingShingle | Na Lin Di Zhang Shanshan Feng Kai Ding Libing Tan Bin Wang Tao Chen Weile Li Xiaoai Dai Jianping Pan Feifei Tang Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost Remote Sensing landslide extraction XGBoost high-resolution remote sensing SHAP Optuna |
| title | Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost |
| title_full | Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost |
| title_fullStr | Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost |
| title_full_unstemmed | Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost |
| title_short | Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost |
| title_sort | rapid landslide extraction from high resolution remote sensing images using shap opt xgboost |
| topic | landslide extraction XGBoost high-resolution remote sensing SHAP Optuna |
| url | https://www.mdpi.com/2072-4292/15/15/3901 |
| work_keys_str_mv | AT nalin rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT dizhang rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT shanshanfeng rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT kaiding rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT libingtan rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT binwang rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT taochen rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT weileli rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT xiaoaidai rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT jianpingpan rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost AT feifeitang rapidlandslideextractionfromhighresolutionremotesensingimagesusingshapoptxgboost |