Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam
Soil Erosion Susceptibility Mapping (SESM) is one of the practical approaches for managing and mitigating soil erosion. This study applied four Machine Learning (ML) models, namely the Multilayer Perceptron (MLP) classifier, AdaBoost, Ridge classifier, and Gradient Boosting classifier to perform SES...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IWA Publishing
2024-01-01
|
Series: | Journal of Hydroinformatics |
Subjects: | |
Online Access: | http://jhydro.iwaponline.com/content/26/1/72 |
_version_ | 1797205125887950848 |
---|---|
author | Chien Quyet Nguyen Tuyen Thi Tran Trang Thanh Thi Nguyen Thuy Ha Thi Nguyen T. S. Astarkhanova Luong Van Vu Khac Tai Dau Hieu Ngoc Nguyen Giang Hương Pham Duc Dam Nguyen Indra Prakash Binh Pham |
author_facet | Chien Quyet Nguyen Tuyen Thi Tran Trang Thanh Thi Nguyen Thuy Ha Thi Nguyen T. S. Astarkhanova Luong Van Vu Khac Tai Dau Hieu Ngoc Nguyen Giang Hương Pham Duc Dam Nguyen Indra Prakash Binh Pham |
author_sort | Chien Quyet Nguyen |
collection | DOAJ |
description | Soil Erosion Susceptibility Mapping (SESM) is one of the practical approaches for managing and mitigating soil erosion. This study applied four Machine Learning (ML) models, namely the Multilayer Perceptron (MLP) classifier, AdaBoost, Ridge classifier, and Gradient Boosting classifier to perform SESM in a region of Nghe An province, Vietnam. The development of these models incorporated seven factors influencing soil erosion: slope degree, slope aspect, curvature, elevation, Normalized Difference Vegetation Index (NDVI), rainfall, and soil type. These factors were determined based on 685 identified soil erosion locations. According to SHapley Additive exPlanations (SHAP) analysis, soil type emerged as the most significant factor influencing soil erosion. Among all the developed models, the Gradient Boosting classifier demonstrated the highest prediction power, followed by the MLP classifier, Ridge classifier, and AdaBoost, respectively. Therefore, the Gradient Boosting classifier is recommended for accurate SESM in other regions too, taking into account the local geo-environmental factors.
HIGHLIGHTS
Soil erosion has been modeled and a soil erosion susceptibility map was generated.;
Several ML models, including the MLP classifier, Ada Boost, Ridge classifier, and Gradient Boosting classifier were implemented.;
Developed models were tuned using the Grid Search CV technique.;
The Gradient Boosting classifier performed the best.;
About 33% of the study area has a high and very high susceptibility to soil erosion occurrence.; |
first_indexed | 2024-03-08T03:17:26Z |
format | Article |
id | doaj.art-2a2b75bd61e54cf28318bde141eb4b8e |
institution | Directory Open Access Journal |
issn | 1464-7141 1465-1734 |
language | English |
last_indexed | 2024-04-24T08:46:09Z |
publishDate | 2024-01-01 |
publisher | IWA Publishing |
record_format | Article |
series | Journal of Hydroinformatics |
spelling | doaj.art-2a2b75bd61e54cf28318bde141eb4b8e2024-04-16T13:30:34ZengIWA PublishingJournal of Hydroinformatics1464-71411465-17342024-01-01261728710.2166/hydro.2023.327327Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, VietnamChien Quyet Nguyen0Tuyen Thi Tran1Trang Thanh Thi Nguyen2Thuy Ha Thi Nguyen3T. S. Astarkhanova4Luong Van Vu5Khac Tai Dau6Hieu Ngoc Nguyen7Giang Hương Pham8Duc Dam Nguyen9Indra Prakash10Binh Pham11 Faculty of Geography, Hanoi National University of Education, Vietnam 136 Xuan Thuy Str., Cau Giay District, Hanoi, Vietnam Faculty of Geography, School of Education, Vinh University, Nghe An, Vietnam Faculty of Geography, School of Education, Vinh University, Nghe An, Vietnam School of Agriculture and Resources, Vinh University, Nghe An, Vietnam Peoples’ Friendship University of Russia, Moscow 117198, Russia School of Agriculture and Resources, Vinh University, Nghe An, Vietnam School of Agriculture and Resources, Vinh University, Nghe An, Vietnam Nghe An University of Economics, Nghe An, Vietnam Faculty of Geography, Thai Nguyen University of Education, Thai Nguyen, Vietnam University of Transport Technology, Hanoi 100000, Vietnam DDG (R) Geological Survey of India, Gandhinagar 382010, India University of Transport Technology, Hanoi 100000, Vietnam Soil Erosion Susceptibility Mapping (SESM) is one of the practical approaches for managing and mitigating soil erosion. This study applied four Machine Learning (ML) models, namely the Multilayer Perceptron (MLP) classifier, AdaBoost, Ridge classifier, and Gradient Boosting classifier to perform SESM in a region of Nghe An province, Vietnam. The development of these models incorporated seven factors influencing soil erosion: slope degree, slope aspect, curvature, elevation, Normalized Difference Vegetation Index (NDVI), rainfall, and soil type. These factors were determined based on 685 identified soil erosion locations. According to SHapley Additive exPlanations (SHAP) analysis, soil type emerged as the most significant factor influencing soil erosion. Among all the developed models, the Gradient Boosting classifier demonstrated the highest prediction power, followed by the MLP classifier, Ridge classifier, and AdaBoost, respectively. Therefore, the Gradient Boosting classifier is recommended for accurate SESM in other regions too, taking into account the local geo-environmental factors. HIGHLIGHTS Soil erosion has been modeled and a soil erosion susceptibility map was generated.; Several ML models, including the MLP classifier, Ada Boost, Ridge classifier, and Gradient Boosting classifier were implemented.; Developed models were tuned using the Grid Search CV technique.; The Gradient Boosting classifier performed the best.; About 33% of the study area has a high and very high susceptibility to soil erosion occurrence.;http://jhydro.iwaponline.com/content/26/1/72gradient boosting classifiermachine learninggrid searchsoil erosionvietnam |
spellingShingle | Chien Quyet Nguyen Tuyen Thi Tran Trang Thanh Thi Nguyen Thuy Ha Thi Nguyen T. S. Astarkhanova Luong Van Vu Khac Tai Dau Hieu Ngoc Nguyen Giang Hương Pham Duc Dam Nguyen Indra Prakash Binh Pham Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam Journal of Hydroinformatics gradient boosting classifier machine learning grid search soil erosion vietnam |
title | Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam |
title_full | Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam |
title_fullStr | Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam |
title_full_unstemmed | Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam |
title_short | Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam |
title_sort | mapping of soil erosion susceptibility using advanced machine learning models at nghe an vietnam |
topic | gradient boosting classifier machine learning grid search soil erosion vietnam |
url | http://jhydro.iwaponline.com/content/26/1/72 |
work_keys_str_mv | AT chienquyetnguyen mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT tuyenthitran mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT trangthanhthinguyen mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT thuyhathinguyen mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT tsastarkhanova mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT luongvanvu mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT khactaidau mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT hieungocnguyen mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT gianghuongpham mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT ducdamnguyen mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT indraprakash mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam AT binhpham mappingofsoilerosionsusceptibilityusingadvancedmachinelearningmodelsatngheanvietnam |