Inundation Height Prediction using Machine Learning with Artificial Neural Network (ANN)

Nabila Siti Burnama; Faizal Immaddudin Wira Rohmat; Mohammad Farid; Hadi Kardhana; Arno Adi Kuntoro

Nabila Siti Burnama Graduate School of Water Resources Engineering, Faculty of Civil Engineering, Bandung Institute of Technology, Jl. Ganesa No. 10 Bandung 40132, Indonesia
Faizal Immaddudin Wira Rohmat Water Resources Development Center, Bandung Institute of Technology, Jl. Ganesa No.10 Bandung 40132, Indonesia
Mohammad Farid Water Resources Research Group, Faculty of Civil Engineering, Bandung Institute of Technology, Jl. Ganesa No.10 Bandung 40132, Indonesia
Hadi Kardhana Water Resources Research Group, Faculty of Civil Engineering, Bandung Institute of Technology, Jl. Ganesa No.10 Bandung 40132, Indonesia
Arno Adi Kuntoro Water Resources Research Group, Faculty of Civil Engineering, Bandung Institute of Technology, Jl. Ganesa No.10 Bandung 40132, Indonesia

Keywords: machine learning, ANN, prediction, mitigation, inundation height

Abstract

Predicting the water level of inundation for the Majalaya Area is important for preventing huge losses because of floods. Because the water level increases rapidly when it rains within one to two hours, and people have time to mitigate. In this study, Machine Learning (ML) with Artificial Neural Network (ANN) method is applied to predict the inundation map in Majalaya Area. Satellite rainfall data from 2014 until 2020, distance to the nearest river, and distance to inflow from Merit DEM are the dependent variables. The inundation height from HEC-RAS extreme rainfall simulation from 2017 until 2020 is the independent variable. All data for the ANN model is divided into training and testing data for machine learning, with 75% data for training and 25% for testing. The results of training machine learning are the inundation height by ANN and inundation height by HEC-RAS have Multiple R-Square (R2) is 0.9212, and for testing data, the R2 is 0.9277. The conclusion is that the machine learning model can predict the inundation height with a high correlation coefficient result. The development of this idea and model is expected to reduce the loss of flooding and improve mitigation.

References

Munoz SE, Giosan L, Therrell MD, Remo JWF, Shen Z, Sullivan RM, et al. Climatic control of Mississippi River flood hazard amplified by river engineering. Nature 2018; 556:95–8. https://doi.org/10.1038/nature26145.

Rosenzweig BR, Herreros Cantis P, Kim Y, Cohn A, Grove K, Brock J, et al. The Value of Urban Flood Modeling. Earths Future 2021;9. https://doi.org/10.1029/2020EF001739.

Chen Y, Syvitski JPM, Gao S, Overeem I, Kettner AJ. Socio- economic impacts on flooding: A 4000-year history of the yellow river, China. Ambio 2012; 41:682–98. https://doi.org/10.1007/s13280-012-0290-5.

Kyselý J, Beranová R. Climate-change effects on extreme precipitation in central Europe: Uncertainties of scenarios based on regional climate models. Theor Appl Climatol 2009; 95:361–74. https://doi.org/10.1007/s00704-008-0014-8.

BNPB Verifikasi 5.402 Kejadian Bencana Sepanjang Tahun 2021 - BNPB 2022. https://bnpb.go.id/berita/bnpb-verifikasi-5-402- kejadian-bencana-sepanjang-tahun-2021 (accessed December 30, 2022).

Nusinovici S, Tham YC, Chak Yan MY, Wei Ting DS, Li J, Sabanayagam C, et al. Logistic regression was as good as machine learning for predicting major chronic diseases. J Clin Epidemiol 2020;122:56–69. https://doi.org/10.1016/j.jclinepi.2020.03.002.

Van Der Ploeg T, Austin PC, Steyerberg EW. Modern modelling techniques are data hungry: A simulation study for predicting dichotomous endpoints. BMC Med Res Methodol 2014;14. https://doi.org/10.1186/1471-2288-14-137.

Dewa Gede A Junnaedhi I, Riawan E, Suwarman R, Wahyu Hadi T, Lubis A, Joko Trilaksono N, et al. Majalaya Flood Early Warning System: A Community Based Approach. IOP Conf Ser Earth Environ Sci, vol. 71, Institute of Physics Publishing; 2017. https://doi.org/10.1088/1755-1315/71/1/012013.

Alam FC, Sembiring E, Muntalif BS, Suendo V. Microplastic distribution in surface water and sediment river around slum and industrial area (case study: Ciwalengke River, Majalaya district, Indonesia). Chemosphere 2019; 224:637–45. https://doi.org/10.1016/j.chemosphere.2019.02.188.

Rohmat FIW, Sa’adi Z, Stamataki I, Kuntoro AA, Farid M, Suwarman R. Flood modeling and baseline study in urban and high population, environment: A case study of Majalaya, Indonesia. Urban Clim 2022;46: 101332. https://doi.org/10.1016/j.uclim.2022.101332.

Garrote J. Free Global DEMs and Flood Modelling—A Comparison Analysis for the January 2015 Flooding Event in Mocuba City (Mozambique). Water (Switzerland) 2022;14. https://doi.org/10.3390/w14020176.

Namara WG, Damisse TA, Tufa FG. Application of HEC-RAS and HEC-GeoRAS model for Flood Inundation Mapping, the case of Awash Bello Flood Plain, Upper Awash River Basin, Oromiya Regional State, Ethiopia. Model Earth Syst Environ 2022;8:1449– 60. https://doi.org/10.1007/s40808-021-01166-9.

Tamiru H, Dinka MO. Application of ANN and HEC-RAS model for flood inundation mapping in lower Baro Akobo River Basin, Ethiopia. J Hydrol Reg Stud 2021;36. https://doi.org/10.1016/j.ejrh.2021.100855.

Jin X, Zhang J, Kong J, Su T, Bai Y. A Reversible Automatic Selection Normalization (RASN) Deep Network for Predicting in the Smart Agriculture System. Agronomy 2022;12. https://doi.org/10.3390/agronomy12030591.

Nwanganga Fred, Chapple Mike. Practical Machine Learning in R. John Wiley & Sons, Incorporated; 2020.

Hand DJ. Classifier technology and the illusion of progress. Statistical Science 2006; 21:1–14. https://doi.org/10.1214/088342306000000060.

Choi SB, Kim WJ, Yoo TK, Park JS, Chung JW, Lee YH, et al. Screening for prediabetes using machine learning models. Comput Math Methods Med 2014; 2014. https://doi.org/10.1155/2014/618976.