Flood susceptibility mapping using Random Forest and Support Vector Machine models with different kernel types
DOI:
https://doi.org/10.11606/eISSN.2236-2878.rdg.2024.213348Keywords:
Geotechnologies; Environmental risk; Disasters; Social vulnerabilityAbstract
The objective of this article was to evaluate the predictive potential of the Random Forest (RF) and Support Vector Machine (SVM) models with different kernel functions for the spatial prediction of flood susceptibility. The study area was the urban watershed of the Castanhal River, located in the eastern Brazilian Amazon. The modeling was based on an inventory of floods recorded from 2020 to 2022 and a geospatial database with the following conditioning factors: altitude, slope, precipitation, aspect, flow power index, topographic humidity index, height above drainage plus proximity (HAND), channel distance, soil profiles and curve number. Five flood susceptibility models were estimated using the Random Forest and Support Vector Machine algorithms with four types of kernel, linear (LN), polynomial (PL), radial basis function (FBR) and sigmoid (SIG). A set of statistical metrics and the area under the curve (AUC) were used to validate the models. The AUC prediction results for the flood susceptibility maps generated by SVM-FBR, SVM-PL, SVM-LN, and SVM-SIG were 98.28%, 97.32%, 96.74%, and 73.35% , respectively. On the other hand, the AUC prediction rate of RF was the highest, 98.94%. The most influential conditioning factors were: altitude, HAND, soil profiles, distance from channels and precipitation. It can be concluded that both RF and SVM are capable of generating efficient and reliable susceptibility models. The resulting susceptibility maps can be beneficial in flood mitigation strategies.
Downloads
References
AMBROISE, B.; BEVEN, K.; FREER, J. Toward a Generalization of the TOPMODEL Concepts: Topographic Indices of Hydrological Similarity. Water Resources Research, v.32, 2135–2145, 1996. DOI:10.1029/95wr03716
BAG, R.; MONDAL, I.; DEHBOZORGI, M.; BANK, S.P.; DAS, D.N.; BANDYOPADHYAY, J.; PHAM, Q.B.; AL-QURAISHI, AYAD M.F.; NGUYEN, X.C.; Modelling and mapping of soil erosion susceptibility using machine learning in a tropical hot sub-humid environment. Journal of Cleaner Production. v.364, 132-428, 2022. DOI: 10.1016/j.jclepro.2022.132428
BATJES, N. H. A world dataset of derived soil properties by FAO-UNESCO soil unit for global modelling. Soil Use and Management, v.13, 9–16, 1997. DOI:10.1111/j.1475-2743.1997.tb00550.x
CARDONA, O. D.; VAN AALST, M. K.; BIRKMANN, J.; FORDHAM, M.; MCGREGOR, G.; PEREZ, R.; PULWARTY, R. S. Determinants of risk: exposure and vulnerability. In Managing the Risks of Extreme Events and Disasters to Advance Climate Change Adaptation. Cambridge University Press. v.1, 65-108, 2012.
CHOUBIN, B.; MORADI, E.; GOLSHAN, M.; ADAMOWSKI J.; SAJEDI-HOSSEINI, F.; MOSAVI, A. An Ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Sci Total Environ. v.651, 2087-2096, 2018. DOI: 10.1016/j.scitotenv.2018.10.064
COSTACHE, R.; ARABAMERI, A.; ELKHRACHY, I.; GHORBANZADEH, O.; PHAM, Q.B. Detection of areas prone to flood risk using state-of-the-art machine learning models. Geomatics, Natural Hazards and Risk. v.12, 1488-1507, 2021. DOI: 10.1080/19475705.2021.1920480
CUREBAL, I.; EFE, R.; OZDEMIR, H.; SOYKAN, A.; SÖNMEZ, S. GIS-based approach for flood analysis: case study of Keçidere flash flood event (Turkey). Geocarto Int. v.31, 355–366, 2016. DOI: 10.1080/10106049.2015.1047411
DARABI, H.; RAHMATI, O.; NAGHIBI, S.A.; MOHAMMADI, F.; AHMADISHARAF, E.; KALANTARI, Z.; HAGHIGHI, A.T.; SOLEIMANPOUR, S.M.; TIEFENBACHER, J.P.; BUI, D.T. Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood. Geocarto International, v.37, 5716-5741, 2022. DOI: 10.1080/10106049.2021.1920629
DARABI, H.; HAGHIGHI, A.T.; MOHAMADI, M.A.; RASHIDPOUR, M.; ZIEGLER, A.D.; HEKMATZADEH, A.A.; KLØVE, B. Urban flood risk mapping using data-driven geospatial techniques for a flood-prone case area in Iran. Hydrology Research. v.51, 127–142, 2020. DOI:10.2166/nh.2019.090
DORMANN, C. F.; ELITH, J.; BACHER, S.; CARRÉ, G. C. G.; GARCÍA MÁRQUEZ, J. R.; GRUBER, B.; LAFOURCADE, B.; LEITAO, P. J.; MÜNKEMÜLLER, T.; MCCLEAN, C. J.; OSBORNE, P. E.; RENEKING, B.; SCHRÖDER, B.; SKIDMORE, A. K.; ZURELL, D.; LAUTENBACH, S. Collinearity. a review of methods to deal with it and a simulation study evaluating their performance: open access. Ecography. v.36, 27-46, 2013. DOI:10.1111/j.1600-0587.2012.07348.x
FLÜGEL, W.A. Delineating hydrological response units by geographical information system analyses for regional hydrological modelling using PRMS/MMS in the drainage basin of the River Bröl, Germany. Hydrological Processes. v.9, 423–436, 1995. DOI:10.1002/hyp.3360090313
GUDIYANGADA, N. T.; TAVAKKOLI, P. S.; GHOLAMNIA, K.; GHORBANZADEH, O.; RAHMATI, O.; BLASCHKE, T. Flood Susceptibility Mapping with Machine Learning, Multi-Criteria Decision Analysis and Ensemble Using Dempster Shafer Theory, Journal of Hydrology. v. 590, 2020, DOI: 10.1016/j.jhydrol.2020.125275
HAIR, J.F.; BLACK, W.C.; BABIN, B.J.; ANDERSON, R.E. Multivariate Data Analysis: Pearson New International Edition. 7.ed. Pearson Education Limited; 2013.
HO, T. K. Random decision forests, Proceedings of 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada, v.1, 278-282, 1995. DOI: 10.1109/ICDAR.1995.598994.
HUBER, S.; RUST, C. Calculate travel time and distance with OpenStreetMap data using the Open Source Routing Machine (OSRM). Stata J. v.16, 416–423, 2016.
LEE, S.; KIM, J.C.; JUNG, H.S.; LEE, M.J.; LEE, S. Predição espacial da suscetibilidade a inundações usando modelos de floresta aleatória e árvores impulsionadas na cidade metropolitana de Seul, Coreia. Geomática, Perigos e Riscos Naturais. v.8, 1185-1203, 2017. DOI: 10.1080/19475705.2017.1308971
MASOOD, M.; TAKEUCHI, K. Assessment of flood hazard, vulnerability and risk of mid-eastern Dhaka using DEM and 1D hydrodynamic model. Nat. Hazards. V.6, 1757–770, 2012. DOI: 10.1007/s11069-011-0060-x
MOSAVI, A.; SAJEDI-HOSSEINI, F.; CHOUBIN, B.; TAROMIDEH, F;HI, G.; DINEVA, A.A. Susceptibility mapping of soil water erosion using machine learning models. Water. v.12, 1-17, 2020, DOI:10.3390/w12071995
NOBRE, A. D.; CUARTAS, L. A.; HODNETT, M.; RENNÓ, C. D.; RODRIGUES, G.; SILVEIRA, A.; WATERLOO, M.; SALESKA, S. Height Above the Nearest Drainage – a hydrologically relevant new terrain model. Journal of Hydrology. v.404, 13–29, 2011. DOI:10.1016/j.jhydrol.2011.03.051
OH, H. J.; PRADHAN, B. Application of a neuro-fuzzy model to landslide-susceptibility mapping for shallow landslides in a tropical hilly area. Computers & Geosciences. v.37, 1264-1276, 2011. DOI:10.1016/j.cageo.2010.10.012
RAHMATI, O. et al. PMT: new analytical framework for automated evaluation of geo-environmental modelling approaches. Sci. Total Environ. 664, 296–311, 2019. DOI: 10.1016/j.scitotenv.2019.02.017
RAHMATI, O.; ZEINIVAND, H.; BESHARAT, M. Flood hazard zoning in Yasooj region, Iran, 533 using GIS and multi-criteria decision analysis. Geomat. Nat. Haz. Risk. v.7, 1000-1017, 2016. DOI: 10.1080/19475705.2015.1045043
RAHMATI, O.; POURGHASEMI, H. R.; ZEINIVAND, H. Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province, Iran. Geocarto International, v.31, 42-70, 2015. doi:10.1080/10106049.2015.1041559
REFSGAARD, J.C. Parameterisation, calibration and validation of distributed hydrological models. Journal of Hydrology, v. 198, p. 69-97, 1997. DOI: 10.1016/s0022-1694(96)03329-2.
RENNÓ, C. D.; NOBRE, A. D.; CUARTAS, L. A.; SOARES, J. V.; HODNETT, M. G.; TOMASELLA, J.; WATERLOO, M.J. HAND, a new terrain descriptor using SRTM-DEM: Mapping terra-firme rainforest environments in Amazonia. Remote Sensing of Environment, v.112, 3469-3481, 2008. DOI: 10.1016/j.rse.2008.03.018
SARTORI, A.; NETO, F. L.; GENOVEZ, A, M. Classificação Hidrológica de Solos Brasileiros para a Estimativa da Chuva Excedente com o Método do Serviço de Conservação do Solo dos Estados Unidos Parte 1: Classificação. RBRH – Revista Brasileira de Recursos Hídricos. v.10, p. 05-18, 2005.
SELEEM, O.; AYZEL, G.; DE SOUZA, A.C.T.; BRONSTERT, A.; HEISTERMANN, M. Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany. Geomatics, Natural Hazards and Risk, v.13, 1640-1662, 2022. DOI: 10.1080/19475705.2022.2097131
TEHRANY, M. S.; PRADHAN, B.; MANSOR, S.; AHMAD, N. Flood susceptibility assessment using GIS-based support vector machine model with diferent kernel types. Catena. v.125, 91–101, 2015. Doi: 10.1016/j.catena.2014.10.017
TEHRANY, M. S.; PRADHAN, B.; JEBUR, M. N. Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. Journal of Hydrology, v.512, 332–343, 2014. DOI: 10.1016/j.jhydrol.2014.03.008
TOMINAGA, L. K; SANTORO, J; AMARAL, R. do (Orgs). Desastres naturais: conhecer para prevenir. 3. ed. São Paulo: Instituto Geológico, 2015. 196 p. il. color. ISBN 978-85-87235-09-1.
VEDOVELLO, R. ;MACEDO, E. S. DE. Deslizamentos de encostas. In: Santos, Rosely Ferreira dos. (org.). Vulnerabilidade ambiental: desastres naturais ou fenômenos induzidos? Brasília, Ministério do Meio Ambiente – MMA, pp. 75-94. 2007.
VOJTEK. M.; VOJTEKOVÁ J. Flood hazard and flood risk assessment at the local spatial scale: a case study. Geomatics, Natural Hazards and Risk. v.7, 1973–1992, 2016. DOI: 10.1080/19475705.2016.1166874
YESILNACAR, E.K. The application of computational intelligence to landslide susceptibility mapping in Turkey. Parkville, Victoria: University of Melbourne; 2005.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Francisco Amaral; Edson Luís Piroli , Viviane Corrêa Santos
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Autores que publicam nesta revista concordam com os seguintes termos:
- Autores mantém os direitos autorais e concedem à revista o direito de primeira publicação, com o trabalho simultaneamente licenciado sob a Licença Creative Commons Attribution BY-NC-SA que permite o compartilhamento do trabalho com reconhecimento da autoria e publicação inicial nesta revista.
- Autores têm autorização para assumir contratos adicionais separadamente, para distribuição não-exclusiva da versão do trabalho publicada nesta revista (ex.: publicar em repositório institucional ou como capítulo de livro), com reconhecimento de autoria e publicação inicial nesta revista. A licença adotada enquadra-se no padrão CC-BY-NC-SA.
- Autores têm permissão e são estimulados a publicar e distribuir seu trabalho online (ex.: em repositórios institucionais ou na sua página pessoal) a qualquer ponto antes ou durante o processo editorial, já que isso pode gerar alterações produtivas, bem como aumentar o impacto e a citação do trabalho publicado (Veja O Efeito do Acesso Livre).
