Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms
In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inve...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-05-01
|
| Series: | Geoscience Frontiers |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1674987120302449 |
| _version_ | 1797707826769952768 |
|---|---|
| author | Abdul-Lateef Balogun Fatemeh Rezaie Quoc Bao Pham Ljubomir Gigović Siniša Drobnjak Yusuf A. Aina Mahdi Panahi Shamsudeen Temitope Yekeen Saro Lee |
| author_facet | Abdul-Lateef Balogun Fatemeh Rezaie Quoc Bao Pham Ljubomir Gigović Siniša Drobnjak Yusuf A. Aina Mahdi Panahi Shamsudeen Temitope Yekeen Saro Lee |
| author_sort | Abdul-Lateef Balogun |
| collection | DOAJ |
| description | In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance. |
| first_indexed | 2024-03-12T06:12:18Z |
| format | Article |
| id | doaj.art-f298fb55ba7f485ba0c6e30714db8fa6 |
| institution | Directory Open Access Journal |
| issn | 1674-9871 |
| language | English |
| last_indexed | 2024-03-12T06:12:18Z |
| publishDate | 2021-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Geoscience Frontiers |
| spelling | doaj.art-f298fb55ba7f485ba0c6e30714db8fa62023-09-03T02:54:47ZengElsevierGeoscience Frontiers1674-98712021-05-01123101104Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithmsAbdul-Lateef Balogun0Fatemeh Rezaie1Quoc Bao Pham2Ljubomir Gigović3Siniša Drobnjak4Yusuf A. Aina5Mahdi Panahi6Shamsudeen Temitope Yekeen7Saro Lee8Geospatial Analysis and Modelling (GAM) Research Group, Department of Civil & Environmental Engineering, Universitit Teknologi PETRONS (UTP), Seri Iskandar 32610, Perak, MalaysiaGeoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124, Gwahak-ro Yuseong-gu, Daejeon 34132, Republic of Korea; Department of Geophysical Exploration, Korea University of Science and Technology, 217 Gajeong-ro Yuseong-gu, Daejeon 34113, Republic of KoreaInstitute of Research and Development, Duy Tan University, Danang 550000, Vietnam; Faculty of Environmental and Chemical Engineering, Duy Tan University, Danang 550000, VietnamDepartment of Geography, University of Defence, 11000 Belgrade, SerbiaMilitary Geographical Institute, 11000 Belgrade, SerbiaDepartment of Geomatics Engineering Technology, Yanbu Industrial College, Yanbu, Saudi ArabiaGeoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124, Gwahak-ro Yuseong-gu, Daejeon 34132, Republic of Korea; Division of Science Education, College of Education, # 4–301, Gangwondaehak-gil Chuncheon-si, Kangwon National University, Gangwon-do 24341, Republic of KoreaGeospatial Analysis and Modelling (GAM) Research Group, Department of Civil & Environmental Engineering, Universitit Teknologi PETRONS (UTP), Seri Iskandar 32610, Perak, MalaysiaGeoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124, Gwahak-ro Yuseong-gu, Daejeon 34132, Republic of Korea; Department of Geophysical Exploration, Korea University of Science and Technology, 217 Gajeong-ro Yuseong-gu, Daejeon 34113, Republic of Korea; Corresponding author at: Geoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124, Gwahak-ro Yuseong-gu, Daejeon 34132, Republic of Korea.In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.http://www.sciencedirect.com/science/article/pii/S1674987120302449LandslideMachine learningMetaheuristicSpatial modelingSupport vector regression |
| spellingShingle | Abdul-Lateef Balogun Fatemeh Rezaie Quoc Bao Pham Ljubomir Gigović Siniša Drobnjak Yusuf A. Aina Mahdi Panahi Shamsudeen Temitope Yekeen Saro Lee Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms Geoscience Frontiers Landslide Machine learning Metaheuristic Spatial modeling Support vector regression |
| title | Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms |
| title_full | Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms |
| title_fullStr | Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms |
| title_full_unstemmed | Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms |
| title_short | Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms |
| title_sort | spatial prediction of landslide susceptibility in western serbia using hybrid support vector regression svr with gwo bat and coa algorithms |
| topic | Landslide Machine learning Metaheuristic Spatial modeling Support vector regression |
| url | http://www.sciencedirect.com/science/article/pii/S1674987120302449 |
| work_keys_str_mv | AT abdullateefbalogun spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT fatemehrezaie spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT quocbaopham spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT ljubomirgigovic spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT sinisadrobnjak spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT yusufaaina spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT mahdipanahi spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT shamsudeentemitopeyekeen spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms AT sarolee spatialpredictionoflandslidesusceptibilityinwesternserbiausinghybridsupportvectorregressionsvrwithgwobatandcoaalgorithms |