A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran)
In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province,...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/11/2444 |
id |
doaj-a17642cd698249a4bf144d9a09330d9f |
---|---|
record_format |
Article |
spelling |
doaj-a17642cd698249a4bf144d9a09330d9f2020-11-25T01:12:18ZengMDPI AGSensors1424-82202019-05-011911244410.3390/s19112444s19112444A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran)Dieu Tien Bui0Ataollah Shirzadi1Himan Shahabi2Kamran Chapi3Ebrahim Omidavr4Binh Thai Pham5Dawood Talebpour Asl6Hossein Khaledian7Biswajeet Pradhan8Mahdi Panahi9Baharin Bin Ahmad10Hosein Rahmani11Gyula Gróf12Saro Lee13Geographic Information Science Research Group, Ton Duc Thang University, Ho Chi Minh City, VietnamDepartment of Rangeland and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranDepartment of Geomorphology, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranDepartment of Rangeland and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranDepartment of Rangeland and Watershed Management, Faculty of Natural Resources and Earth Sciences, University of Kashan, Kashan 87317-53153, IranInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamDepartment of Geomorphology, Faculty of Natural Resources, University of Kurdistan, Sanandaj 66177-15175, IranKurdistan Agriculture and Natural Resources Research and Education Center, AREEO, Sanandaj 66169-36311, IranCenter for Advanced Modeling and Geospatial System (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, CB11.06.106, Building 11, 81 Broadway, Ultimo NSW 2007, AustraliaDepartment of Geophysics, Young Researchers and Elites Club, North Tehran Branch, Islamic Azad University, Tehran P.O. Box 19585/466, IranFaculty of Built Environment and Surveying, Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, MalaysiaDepartment of Computer Science and Engineering, and IT, School of Electrical and Computer Engineering, Shiraz University, Shiraz 84334-71964, IranDepartment of Energy Engineering, Budapest University of Technology and Economics, Budapest 1111, HungaryGeoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124 Gwahak-ro Yuseong-gu, Daejeon 34132, KoreaIn this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811).https://www.mdpi.com/1424-8220/19/11/2444gully erosionmachine learningensemble algorithmsgeomorphologyGeographic information scienceKurdistan province |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Dieu Tien Bui Ataollah Shirzadi Himan Shahabi Kamran Chapi Ebrahim Omidavr Binh Thai Pham Dawood Talebpour Asl Hossein Khaledian Biswajeet Pradhan Mahdi Panahi Baharin Bin Ahmad Hosein Rahmani Gyula Gróf Saro Lee |
spellingShingle |
Dieu Tien Bui Ataollah Shirzadi Himan Shahabi Kamran Chapi Ebrahim Omidavr Binh Thai Pham Dawood Talebpour Asl Hossein Khaledian Biswajeet Pradhan Mahdi Panahi Baharin Bin Ahmad Hosein Rahmani Gyula Gróf Saro Lee A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) Sensors gully erosion machine learning ensemble algorithms geomorphology Geographic information science Kurdistan province |
author_facet |
Dieu Tien Bui Ataollah Shirzadi Himan Shahabi Kamran Chapi Ebrahim Omidavr Binh Thai Pham Dawood Talebpour Asl Hossein Khaledian Biswajeet Pradhan Mahdi Panahi Baharin Bin Ahmad Hosein Rahmani Gyula Gróf Saro Lee |
author_sort |
Dieu Tien Bui |
title |
A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) |
title_short |
A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) |
title_full |
A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) |
title_fullStr |
A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) |
title_full_unstemmed |
A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) |
title_sort |
novel ensemble artificial intelligence approach for gully erosion mapping in a semi-arid watershed (iran) |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-05-01 |
description |
In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811). |
topic |
gully erosion machine learning ensemble algorithms geomorphology Geographic information science Kurdistan province |
url |
https://www.mdpi.com/1424-8220/19/11/2444 |
work_keys_str_mv |
AT dieutienbui anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT ataollahshirzadi anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT himanshahabi anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT kamranchapi anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT ebrahimomidavr anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT binhthaipham anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT dawoodtalebpourasl anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT hosseinkhaledian anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT biswajeetpradhan anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT mahdipanahi anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT baharinbinahmad anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT hoseinrahmani anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT gyulagrof anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT sarolee anovelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT dieutienbui novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT ataollahshirzadi novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT himanshahabi novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT kamranchapi novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT ebrahimomidavr novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT binhthaipham novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT dawoodtalebpourasl novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT hosseinkhaledian novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT biswajeetpradhan novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT mahdipanahi novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT baharinbinahmad novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT hoseinrahmani novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT gyulagrof novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran AT sarolee novelensembleartificialintelligenceapproachforgullyerosionmappinginasemiaridwatershediran |
_version_ |
1725167148486098944 |