Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility
The extreme form of land degradation caused by the formation of gullies is a major challenge for the sustainability of land resources. This problem is more vulnerable in the arid and semi-arid environment and associated damage to agriculture and allied economic activities. Appropriate modeling of su...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/17/2833 |
| _version_ | 1797554918445285376 |
|---|---|
| author | Alireza Arabameri Omid Asadi Nalivan Subodh Chandra Pal Rabin Chakrabortty Asish Saha Saro Lee Biswajeet Pradhan Dieu Tien Bui |
| author_facet | Alireza Arabameri Omid Asadi Nalivan Subodh Chandra Pal Rabin Chakrabortty Asish Saha Saro Lee Biswajeet Pradhan Dieu Tien Bui |
| author_sort | Alireza Arabameri |
| collection | DOAJ |
| description | The extreme form of land degradation caused by the formation of gullies is a major challenge for the sustainability of land resources. This problem is more vulnerable in the arid and semi-arid environment and associated damage to agriculture and allied economic activities. Appropriate modeling of such erosion is therefore needed with optimum accuracy for estimating vulnerable regions and taking appropriate initiatives. The Golestan Dam has faced an acute problem of gully erosion over the last decade and has adversely affected society. Here, the artificial neural network (ANN), general linear model (GLM), maximum entropy (MaxEnt), and support vector machine (SVM) machine learning algorithm with 90/10, 80/20, 70/30, 60/40, and 50/50 random partitioning of training and validation samples was selected purposively for estimating the gully erosion susceptibility. The main objective of this work was to predict the susceptible zone with the maximum possible accuracy. For this purpose, random partitioning approaches were implemented. For this purpose, 20 gully erosion conditioning factors were considered for predicting the susceptible areas by considering the multi-collinearity test. The variance inflation factor (VIF) and tolerance (TOL) limit were considered for multi-collinearity assessment for reducing the error of the models and increase the efficiency of the outcome. The ANN with 50/50 random partitioning of the sample is the most optimal model in this analysis. The area under curve (AUC) values of receiver operating characteristics (ROC) in ANN (50/50) for the training and validation data are 0.918 and 0.868, respectively. The importance of the causative factors was estimated with the help of the Jackknife test, which reveals that the most important factor is the topography position index (TPI). Apart from this, the prioritization of all predicted models was estimated taking into account the training and validation data set, which should help future researchers to select models from this perspective. This type of outcome should help planners and local stakeholders to implement appropriate land and water conservation measures. |
| first_indexed | 2024-03-10T16:38:55Z |
| format | Article |
| id | doaj.art-96f681c26e9d4b2789e514ed6b30dd6b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T16:38:55Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-96f681c26e9d4b2789e514ed6b30dd6b2023-11-20T12:10:18ZengMDPI AGRemote Sensing2072-42922020-09-011217283310.3390/rs12172833Novel Machine Learning Approaches for Modelling the Gully Erosion SusceptibilityAlireza Arabameri0Omid Asadi Nalivan1Subodh Chandra Pal2Rabin Chakrabortty3Asish Saha4Saro Lee5Biswajeet Pradhan6Dieu Tien Bui7Department of Geomorphology, Tarbiat Modares University, Tehran 14117-13116, IranDepartment of Watershed Management, Gorgan University of Agricultural Sciences and Natural Resources (GUASNR), Gorgan 3184761174, IranDepartment of Geography, The University of Burdwan, West Bengal 713104, IndiaDepartment of Geography, The University of Burdwan, West Bengal 713104, IndiaDepartment of Geography, The University of Burdwan, West Bengal 713104, IndiaGeoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124 Gwahak-ro Yuseong-gu, Daejeon 34132, KoreaCentre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, AustraliaInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamThe extreme form of land degradation caused by the formation of gullies is a major challenge for the sustainability of land resources. This problem is more vulnerable in the arid and semi-arid environment and associated damage to agriculture and allied economic activities. Appropriate modeling of such erosion is therefore needed with optimum accuracy for estimating vulnerable regions and taking appropriate initiatives. The Golestan Dam has faced an acute problem of gully erosion over the last decade and has adversely affected society. Here, the artificial neural network (ANN), general linear model (GLM), maximum entropy (MaxEnt), and support vector machine (SVM) machine learning algorithm with 90/10, 80/20, 70/30, 60/40, and 50/50 random partitioning of training and validation samples was selected purposively for estimating the gully erosion susceptibility. The main objective of this work was to predict the susceptible zone with the maximum possible accuracy. For this purpose, random partitioning approaches were implemented. For this purpose, 20 gully erosion conditioning factors were considered for predicting the susceptible areas by considering the multi-collinearity test. The variance inflation factor (VIF) and tolerance (TOL) limit were considered for multi-collinearity assessment for reducing the error of the models and increase the efficiency of the outcome. The ANN with 50/50 random partitioning of the sample is the most optimal model in this analysis. The area under curve (AUC) values of receiver operating characteristics (ROC) in ANN (50/50) for the training and validation data are 0.918 and 0.868, respectively. The importance of the causative factors was estimated with the help of the Jackknife test, which reveals that the most important factor is the topography position index (TPI). Apart from this, the prioritization of all predicted models was estimated taking into account the training and validation data set, which should help future researchers to select models from this perspective. This type of outcome should help planners and local stakeholders to implement appropriate land and water conservation measures.https://www.mdpi.com/2072-4292/12/17/2833land degradationgully erosionrandom partitioning approachesmachine learning algorithmjackknife test |
| spellingShingle | Alireza Arabameri Omid Asadi Nalivan Subodh Chandra Pal Rabin Chakrabortty Asish Saha Saro Lee Biswajeet Pradhan Dieu Tien Bui Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility Remote Sensing land degradation gully erosion random partitioning approaches machine learning algorithm jackknife test |
| title | Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility |
| title_full | Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility |
| title_fullStr | Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility |
| title_full_unstemmed | Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility |
| title_short | Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility |
| title_sort | novel machine learning approaches for modelling the gully erosion susceptibility |
| topic | land degradation gully erosion random partitioning approaches machine learning algorithm jackknife test |
| url | https://www.mdpi.com/2072-4292/12/17/2833 |
| work_keys_str_mv | AT alirezaarabameri novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT omidasadinalivan novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT subodhchandrapal novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT rabinchakrabortty novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT asishsaha novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT sarolee novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT biswajeetpradhan novelmachinelearningapproachesformodellingthegullyerosionsusceptibility AT dieutienbui novelmachinelearningapproachesformodellingthegullyerosionsusceptibility |