Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data
Piping erosion is one form of water erosion that leads to significant changes in the landscape and environmental degradation. In the present study, we evaluated piping erosion modeling in the Zarandieh watershed of Markazi province in Iran based on random forest (RF), support vector machine (SVM), a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/9/10/346 |
| _version_ | 1797552868106960896 |
|---|---|
| author | Shahab S. Band Saeid Janizadeh Sunil Saha Kaustuv Mukherjee Saeid Khosrobeigi Bozchaloei Artemi Cerdà Manouchehr Shokri Amirhosein Mosavi |
| author_facet | Shahab S. Band Saeid Janizadeh Sunil Saha Kaustuv Mukherjee Saeid Khosrobeigi Bozchaloei Artemi Cerdà Manouchehr Shokri Amirhosein Mosavi |
| author_sort | Shahab S. Band |
| collection | DOAJ |
| description | Piping erosion is one form of water erosion that leads to significant changes in the landscape and environmental degradation. In the present study, we evaluated piping erosion modeling in the Zarandieh watershed of Markazi province in Iran based on random forest (RF), support vector machine (SVM), and Bayesian generalized linear models (Bayesian GLM) machine learning algorithms. For this goal, due to the importance of various geo-environmental and soil properties in the evolution and creation of piping erosion, 18 variables were considered for modeling the piping erosion susceptibility in the Zarandieh watershed. A total of 152 points of piping erosion were recognized in the study area that were divided into training (70%) and validation (30%) for modeling. The area under curve (AUC) was used to assess the effeciency of the RF, SVM, and Bayesian GLM. Piping erosion susceptibility results indicated that all three RF, SVM, and Bayesian GLM models had high efficiency in the testing step, such as the AUC shown with values of 0.9 for RF, 0.88 for SVM, and 0.87 for Bayesian GLM. Altitude, pH, and bulk density were the variables that had the greatest influence on the piping erosion susceptibility in the Zarandieh watershed. This result indicates that geo-environmental and soil chemical variables are accountable for the expansion of piping erosion in the Zarandieh watershed. |
| first_indexed | 2024-03-10T16:07:08Z |
| format | Article |
| id | doaj.art-ea88e91601f54ae99ee41588666984a1 |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-10T16:07:08Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-ea88e91601f54ae99ee41588666984a12023-11-20T14:51:03ZengMDPI AGLand2073-445X2020-09-0191034610.3390/land9100346Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR DataShahab S. Band0Saeid Janizadeh1Sunil Saha2Kaustuv Mukherjee3Saeid Khosrobeigi Bozchaloei4Artemi Cerdà5Manouchehr Shokri6Amirhosein Mosavi7Institute of Research and Development, Duy Tan University, Da Nang 550000, VietnamDepartment of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, Tehran 14115-111, IranDepartment of Geography, University of Gour Banga, Malda, West Bengal 732103, IndiaDepartment of Geography, Chandidas Mahavidyalaya, Birbhum, West Bengal 731215, IndiaDepartment of Watershed Management Engineering and Sciences, Faculty in Agriculture and Natural Resources, Tehran University, Tehran 14174-14418, IranSoil Erosion and Degradation Research Group, Department of Geography, Valencia University, Blasco Ibàñez 28, 46010 Valencia, SpainFaculty of Civil Engineering, Bauhaus-Universität Weimar, 99423 Weimar, GermanyEnvironmental Quality, Atmospheric Science and Climate Change Research Group, Ton Duc Thang University, Ho Chi Minh City, VietnamPiping erosion is one form of water erosion that leads to significant changes in the landscape and environmental degradation. In the present study, we evaluated piping erosion modeling in the Zarandieh watershed of Markazi province in Iran based on random forest (RF), support vector machine (SVM), and Bayesian generalized linear models (Bayesian GLM) machine learning algorithms. For this goal, due to the importance of various geo-environmental and soil properties in the evolution and creation of piping erosion, 18 variables were considered for modeling the piping erosion susceptibility in the Zarandieh watershed. A total of 152 points of piping erosion were recognized in the study area that were divided into training (70%) and validation (30%) for modeling. The area under curve (AUC) was used to assess the effeciency of the RF, SVM, and Bayesian GLM. Piping erosion susceptibility results indicated that all three RF, SVM, and Bayesian GLM models had high efficiency in the testing step, such as the AUC shown with values of 0.9 for RF, 0.88 for SVM, and 0.87 for Bayesian GLM. Altitude, pH, and bulk density were the variables that had the greatest influence on the piping erosion susceptibility in the Zarandieh watershed. This result indicates that geo-environmental and soil chemical variables are accountable for the expansion of piping erosion in the Zarandieh watershed.https://www.mdpi.com/2073-445X/9/10/346random forestsupport vector machineBayesian generalized linear model (Bayesian GLM)machine learningsusceptibilityspatial modeling |
| spellingShingle | Shahab S. Band Saeid Janizadeh Sunil Saha Kaustuv Mukherjee Saeid Khosrobeigi Bozchaloei Artemi Cerdà Manouchehr Shokri Amirhosein Mosavi Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data Land random forest support vector machine Bayesian generalized linear model (Bayesian GLM) machine learning susceptibility spatial modeling |
| title | Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data |
| title_full | Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data |
| title_fullStr | Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data |
| title_full_unstemmed | Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data |
| title_short | Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data |
| title_sort | evaluating the efficiency of different regression decision tree and bayesian machine learning algorithms in spatial piping erosion susceptibility using alos palsar data |
| topic | random forest support vector machine Bayesian generalized linear model (Bayesian GLM) machine learning susceptibility spatial modeling |
| url | https://www.mdpi.com/2073-445X/9/10/346 |
| work_keys_str_mv | AT shahabsband evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT saeidjanizadeh evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT sunilsaha evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT kaustuvmukherjee evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT saeidkhosrobeigibozchaloei evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT artemicerda evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT manouchehrshokri evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata AT amirhoseinmosavi evaluatingtheefficiencyofdifferentregressiondecisiontreeandbayesianmachinelearningalgorithmsinspatialpipingerosionsusceptibilityusingalospalsardata |