Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models
Gully erosion is the most severe type of water erosion and is a major land degradation process. Gully erosion susceptibility mapping (GESM)’s efficiency and interpretability remains a challenge, especially in complex terrain areas. In this study, a WoE-MLC model was used to solve the above problem,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/10/10/680 |
| _version_ | 1797514357754560512 |
|---|---|
| author | Annan Yang Chunmei Wang Guowei Pang Yongqing Long Lei Wang Richard M. Cruse Qinke Yang |
| author_facet | Annan Yang Chunmei Wang Guowei Pang Yongqing Long Lei Wang Richard M. Cruse Qinke Yang |
| author_sort | Annan Yang |
| collection | DOAJ |
| description | Gully erosion is the most severe type of water erosion and is a major land degradation process. Gully erosion susceptibility mapping (GESM)’s efficiency and interpretability remains a challenge, especially in complex terrain areas. In this study, a WoE-MLC model was used to solve the above problem, which combines machine learning classification algorithms and the statistical weight of evidence (WoE) model in the Loess Plateau. The three machine learning (ML) algorithms utilized in this research were random forest (RF), gradient boosted decision trees (GBDT), and extreme gradient boosting (XGBoost). The results showed that: (1) GESM were well predicted by combining both machine learning regression models and WoE-MLC models, with the area under the curve (AUC) values both greater than 0.92, and the latter was more computationally efficient and interpretable; (2) The XGBoost algorithm was more efficient in GESM than the other two algorithms, with the strongest generalization ability and best performance in avoiding overfitting (averaged AUC = 0.947), followed by the RF algorithm (averaged AUC = 0.944), and GBDT algorithm (averaged AUC = 0.938); and (3) slope gradient, land use, and altitude were the main factors for GESM. This study may provide a possible method for gully erosion susceptibility mapping at large scale. |
| first_indexed | 2024-03-10T06:30:29Z |
| format | Article |
| id | doaj.art-188941c2f34245c4837ad62b7c370de5 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T06:30:29Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-188941c2f34245c4837ad62b7c370de52023-11-22T18:29:52ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-10-01101068010.3390/ijgi10100680Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning ModelsAnnan Yang0Chunmei Wang1Guowei Pang2Yongqing Long3Lei Wang4Richard M. Cruse5Qinke Yang6Shaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi’an 710127, ChinaShaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi’an 710127, ChinaShaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi’an 710127, ChinaShaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi’an 710127, ChinaShaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi’an 710127, ChinaDepartment of Agronomy, Iowa State University, Ames, IA 50011, USAShaanxi Key Laboratory of Earth Surface System and Environmental Carrying Capacity, College of Urban and Environmental Sciences, Northwest University, Xi’an 710127, ChinaGully erosion is the most severe type of water erosion and is a major land degradation process. Gully erosion susceptibility mapping (GESM)’s efficiency and interpretability remains a challenge, especially in complex terrain areas. In this study, a WoE-MLC model was used to solve the above problem, which combines machine learning classification algorithms and the statistical weight of evidence (WoE) model in the Loess Plateau. The three machine learning (ML) algorithms utilized in this research were random forest (RF), gradient boosted decision trees (GBDT), and extreme gradient boosting (XGBoost). The results showed that: (1) GESM were well predicted by combining both machine learning regression models and WoE-MLC models, with the area under the curve (AUC) values both greater than 0.92, and the latter was more computationally efficient and interpretable; (2) The XGBoost algorithm was more efficient in GESM than the other two algorithms, with the strongest generalization ability and best performance in avoiding overfitting (averaged AUC = 0.947), followed by the RF algorithm (averaged AUC = 0.944), and GBDT algorithm (averaged AUC = 0.938); and (3) slope gradient, land use, and altitude were the main factors for GESM. This study may provide a possible method for gully erosion susceptibility mapping at large scale.https://www.mdpi.com/2220-9964/10/10/680gully erosionmachine learningthe weight of evidencegully erosion susceptibility mappingLoess Plateau |
| spellingShingle | Annan Yang Chunmei Wang Guowei Pang Yongqing Long Lei Wang Richard M. Cruse Qinke Yang Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models ISPRS International Journal of Geo-Information gully erosion machine learning the weight of evidence gully erosion susceptibility mapping Loess Plateau |
| title | Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models |
| title_full | Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models |
| title_fullStr | Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models |
| title_full_unstemmed | Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models |
| title_short | Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models |
| title_sort | gully erosion susceptibility mapping in highly complex terrain using machine learning models |
| topic | gully erosion machine learning the weight of evidence gully erosion susceptibility mapping Loess Plateau |
| url | https://www.mdpi.com/2220-9964/10/10/680 |
| work_keys_str_mv | AT annanyang gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels AT chunmeiwang gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels AT guoweipang gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels AT yongqinglong gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels AT leiwang gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels AT richardmcruse gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels AT qinkeyang gullyerosionsusceptibilitymappinginhighlycomplexterrainusingmachinelearningmodels |