DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning
Soil erosion is a form of land degradation. It is the process of moving surface soil with the action of external forces such as wind or water. Tillage also causes soil erosion. As outlined by the United Nations Sustainable Development Goal (UN SDG) #15, it is a global challenge to “combat desertific...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2220-9964/10/7/452 |
id |
doaj-cdd2317246f143e48333390c51bd1ec4 |
---|---|
record_format |
Article |
spelling |
doaj-cdd2317246f143e48333390c51bd1ec42021-07-23T13:44:58ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-07-011045245210.3390/ijgi10070452DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine LearningKieu Anh Nguyen0Walter Chen1Department of Civil Engineering, National Taipei University of Technology, Taipei 10608, TaiwanDepartment of Civil Engineering, National Taipei University of Technology, Taipei 10608, TaiwanSoil erosion is a form of land degradation. It is the process of moving surface soil with the action of external forces such as wind or water. Tillage also causes soil erosion. As outlined by the United Nations Sustainable Development Goal (UN SDG) #15, it is a global challenge to “combat desertification, and halt and reverse land degradation and halt biodiversity loss.” In order to advance this goal, we studied and modeled the soil erosion depth of a typical watershed in Taiwan using 26 morphometric factors derived from a digital elevation model (DEM) and 10 environmental factors. Feature selection was performed using the Boruta algorithm to determine 15 factors with confirmed importance and one tentative factor. Then, machine learning models, including the random forest (RF) and gradient boosting machine (GBM), were used to create prediction models validated by erosion pin measurements. The results show that GBM, coupled with 15 important factors (confirmed), achieved the best result in the context of root mean square error (RMSE) and Nash–Sutcliffe efficiency (NSE). Finally, we present the maps of soil erosion depth using the two machine learning models. The maps are useful for conservation planning and mitigating future soil erosion.https://www.mdpi.com/2220-9964/10/7/452soil erosionerosion pinmachine learningmorphometric factorShihmen Reservoir watershed |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kieu Anh Nguyen Walter Chen |
spellingShingle |
Kieu Anh Nguyen Walter Chen DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning ISPRS International Journal of Geo-Information soil erosion erosion pin machine learning morphometric factor Shihmen Reservoir watershed |
author_facet |
Kieu Anh Nguyen Walter Chen |
author_sort |
Kieu Anh Nguyen |
title |
DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning |
title_short |
DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning |
title_full |
DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning |
title_fullStr |
DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning |
title_full_unstemmed |
DEM- and GIS-Based Analysis of Soil Erosion Depth Using Machine Learning |
title_sort |
dem- and gis-based analysis of soil erosion depth using machine learning |
publisher |
MDPI AG |
series |
ISPRS International Journal of Geo-Information |
issn |
2220-9964 |
publishDate |
2021-07-01 |
description |
Soil erosion is a form of land degradation. It is the process of moving surface soil with the action of external forces such as wind or water. Tillage also causes soil erosion. As outlined by the United Nations Sustainable Development Goal (UN SDG) #15, it is a global challenge to “combat desertification, and halt and reverse land degradation and halt biodiversity loss.” In order to advance this goal, we studied and modeled the soil erosion depth of a typical watershed in Taiwan using 26 morphometric factors derived from a digital elevation model (DEM) and 10 environmental factors. Feature selection was performed using the Boruta algorithm to determine 15 factors with confirmed importance and one tentative factor. Then, machine learning models, including the random forest (RF) and gradient boosting machine (GBM), were used to create prediction models validated by erosion pin measurements. The results show that GBM, coupled with 15 important factors (confirmed), achieved the best result in the context of root mean square error (RMSE) and Nash–Sutcliffe efficiency (NSE). Finally, we present the maps of soil erosion depth using the two machine learning models. The maps are useful for conservation planning and mitigating future soil erosion. |
topic |
soil erosion erosion pin machine learning morphometric factor Shihmen Reservoir watershed |
url |
https://www.mdpi.com/2220-9964/10/7/452 |
work_keys_str_mv |
AT kieuanhnguyen demandgisbasedanalysisofsoilerosiondepthusingmachinelearning AT walterchen demandgisbasedanalysisofsoilerosiondepthusingmachinelearning |
_version_ |
1721288060725886976 |