Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms
Recurrent floods are one of the major global threats among people, particularly in developing countries like India, as this nation has a tropical monsoon type of climate. Therefore, flood susceptibility (FS) mapping is indeed necessary to overcome this type of natural hazard phenomena. With this in...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/2/241 |
| _version_ | 1797409557111111680 |
|---|---|
| author | Asish Saha Subodh Chandra Pal Alireza Arabameri Thomas Blaschke Somayeh Panahi Indrajit Chowdhuri Rabin Chakrabortty Romulus Costache Aman Arora |
| author_facet | Asish Saha Subodh Chandra Pal Alireza Arabameri Thomas Blaschke Somayeh Panahi Indrajit Chowdhuri Rabin Chakrabortty Romulus Costache Aman Arora |
| author_sort | Asish Saha |
| collection | DOAJ |
| description | Recurrent floods are one of the major global threats among people, particularly in developing countries like India, as this nation has a tropical monsoon type of climate. Therefore, flood susceptibility (FS) mapping is indeed necessary to overcome this type of natural hazard phenomena. With this in mind, we evaluated the prediction performance of FS mapping in the Koiya River basin, Eastern India. The present research work was done through preparation of a sophisticated flood inventory map; eight flood conditioning variables were selected based on the topography and hydro-climatological condition, and by applying the novel ensemble approach of hyperpipes (HP) and support vector regression (SVR) machine learning (ML) algorithms. The ensemble approach of HP-SVR was also compared with the stand-alone ML algorithms of HP and SVR. In relative importance of variables, distance to river was the most dominant factor for flood occurrences followed by rainfall, land use land cover (LULC), and normalized difference vegetation index (NDVI). The validation and accuracy assessment of FS maps was done through five popular statistical methods. The result of accuracy evaluation showed that the ensemble approach is the most optimal model (AUC = 0.915, sensitivity = 0.932, specificity = 0.902, accuracy = 0.928 and Kappa = 0.835) in FS assessment, followed by HP (AUC = 0.885) and SVR (AUC = 0.871). |
| first_indexed | 2024-03-09T04:17:17Z |
| format | Article |
| id | doaj.art-a86384bf279e4249b08610ab23bf5620 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T04:17:17Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-a86384bf279e4249b08610ab23bf56202023-12-03T13:52:51ZengMDPI AGWater2073-44412021-01-0113224110.3390/w13020241Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression AlgorithmsAsish Saha0Subodh Chandra Pal1Alireza Arabameri2Thomas Blaschke3Somayeh Panahi4Indrajit Chowdhuri5Rabin Chakrabortty6Romulus Costache7Aman Arora8Department of Geography, The University of Burdwan, Bardhaman 713104, West Bengal, IndiaDepartment of Geography, The University of Burdwan, Bardhaman 713104, West Bengal, IndiaDepartment of Geomorphology, Tarbiat Modares University, Tehran 14117-13116, IranDepartment of Geoinformatics–Z_GIS, University of Salzburg, 5020 Salzburg, AustriaDepartment of Computer Engineering, Faculty of Valiasr, Tehran Branch, Technical and Vocational University (TVU), Tehran 14356-61137, IranDepartment of Geography, The University of Burdwan, Bardhaman 713104, West Bengal, IndiaDepartment of Geography, The University of Burdwan, Bardhaman 713104, West Bengal, IndiaResearch Institute of the University of Bucharest, 90–92 Sos. Panduri, 5th District, 050107 Bucharest, RomaniaUniversity Center for Research & Development (UCRD), Chandigarh University, Mohali 140413, Punjab, IndiaRecurrent floods are one of the major global threats among people, particularly in developing countries like India, as this nation has a tropical monsoon type of climate. Therefore, flood susceptibility (FS) mapping is indeed necessary to overcome this type of natural hazard phenomena. With this in mind, we evaluated the prediction performance of FS mapping in the Koiya River basin, Eastern India. The present research work was done through preparation of a sophisticated flood inventory map; eight flood conditioning variables were selected based on the topography and hydro-climatological condition, and by applying the novel ensemble approach of hyperpipes (HP) and support vector regression (SVR) machine learning (ML) algorithms. The ensemble approach of HP-SVR was also compared with the stand-alone ML algorithms of HP and SVR. In relative importance of variables, distance to river was the most dominant factor for flood occurrences followed by rainfall, land use land cover (LULC), and normalized difference vegetation index (NDVI). The validation and accuracy assessment of FS maps was done through five popular statistical methods. The result of accuracy evaluation showed that the ensemble approach is the most optimal model (AUC = 0.915, sensitivity = 0.932, specificity = 0.902, accuracy = 0.928 and Kappa = 0.835) in FS assessment, followed by HP (AUC = 0.885) and SVR (AUC = 0.871).https://www.mdpi.com/2073-4441/13/2/241flood susceptibility assessmentKoiya River basinhyperpipes (HP)support vector regression (SVR)ensemble approach |
| spellingShingle | Asish Saha Subodh Chandra Pal Alireza Arabameri Thomas Blaschke Somayeh Panahi Indrajit Chowdhuri Rabin Chakrabortty Romulus Costache Aman Arora Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms Water flood susceptibility assessment Koiya River basin hyperpipes (HP) support vector regression (SVR) ensemble approach |
| title | Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms |
| title_full | Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms |
| title_fullStr | Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms |
| title_full_unstemmed | Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms |
| title_short | Flood Susceptibility Assessment Using Novel Ensemble of Hyperpipes and Support Vector Regression Algorithms |
| title_sort | flood susceptibility assessment using novel ensemble of hyperpipes and support vector regression algorithms |
| topic | flood susceptibility assessment Koiya River basin hyperpipes (HP) support vector regression (SVR) ensemble approach |
| url | https://www.mdpi.com/2073-4441/13/2/241 |
| work_keys_str_mv | AT asishsaha floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT subodhchandrapal floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT alirezaarabameri floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT thomasblaschke floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT somayehpanahi floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT indrajitchowdhuri floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT rabinchakrabortty floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT romuluscostache floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms AT amanarora floodsusceptibilityassessmentusingnovelensembleofhyperpipesandsupportvectorregressionalgorithms |