A Rapid Prediction Model of Urban Flood Inundation in a High-Risk Area Coupling Machine Learning and Numerical Simulation Approaches

Abstract

Climate change has led to increasing frequency of sudden extreme heavy rainfall events in cities, resulting in great disaster losses. Therefore, in emergency management, we need to be timely in predicting urban floods. Although the existing machine learning models can quickly predict the depth of stagnant water, these models only target single points and require large amounts of measured data, which are currently lacking. Although numerical models can accurately simulate and predict such events, it takes a long time to perform the associated calculations, especially two-dimensional large-scale calculations, which cannot meet the needs of emergency management. Therefore, this article proposes a method of coupling neural networks and numerical models that can simulate and identify areas at high risk from urban floods and quickly predict the depth of water accumulation in these areas. Taking a drainage area in Tianjin Municipality, China, as an example, the results show that the simulation accuracy of this method is high, the Nash coefficient is 0.876, and the calculation time is 20 seconds. This method can quickly and accurately simulate the depth of water accumulation in high-risk areas in cities and provide technical support for urban flood emergency management.

Keywords

Flood inundation / Neural networks / Numerical simulations / Rapid prediction / Spatiotemporal prediction / China

References

[1] Ahiablame L, Shakya R. Modeling flood reduction effects of low impact development at a watershed scale. Journal of Environmental Management, 2016, 171: 81-91

[2] Banik BK, Alfonso L, Torres AS, Mynett A, Cristo CD, Leopardi A. Optimal placement of water quality monitoring stations in sewer systems: An information theory approach. Procedia Engineering, 2015, 119: 1308-1317

[3] Beck J. Comparison of three methodologies for Quasi-2D river flood modeling with SWMM5. Journal of Water Management Modeling, 2016

[4] Bowes, B.D., J.M. Sadler, M.M. Morsy, M. Behl, and J.L. Goodall. 2019. Forecasting groundwater table in a flood prone coastal city with long short-term memory and recurrent neural networks. Water 11(5): Article 1098.

[5] Guo, Z., J.P. Leitao, N.E. Simoes, and V. Moosavi. 2020. Data-driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks. Journal of Flood Risk Management 14(1): Article e12684.

[6] Hammond MJ, Chen AS, Djordjevic S, Butler D, Mark O. Urban flood impact assessment: A state-of-the-art review. Urban Water Journal, 2015, 12(1–2): 14-29

[7] Hou JM, Zhou N, Chen G, Huang M, Bai G. Rapid forecasting of urban flood inundation using multiple machine learning models. Natural Hazards, 2021

[8] Huang, G.R., X. Wang, and W. Huang. 2017. Simulation of rainstorm water logging in urban area based on InfoWorks ICM Model. Water Resources and Power 35(2): 66–70; 60 (in Chinese).

[9] Huang, J.H., C. Wang, and Z.H. Fan. 2020. Evolution of design rainfall pattern in Tianjin. Water Resources Protection 36(1): 38–43 (in Chinese).

[10] Huff FA. Time distributions of heavy rainstorms in Illinois. Water Resources Research, 1967, 3(4): 1007-1019

[11] Kabir S, Patidar S, Xia XL, Liang QH, Neal J, Pender G. A deep convolutional neural network model for rapid prediction of fluvial flood inundation. Journal of Hydrology, 2020, 590: 2335-2356

[12] Keifer CJ, Chu HH. Synthetic storm pattern for drainage design. Journal of Hydraulics Division, 1957, 83: 1-25

[13] Kim HI, Han KY. Data-driven approach for the rapid simulation of urban flood prediction. KSCE Journal of Civil Engineering, 2020, 24: 1932-1943

[14] Kim, H.I., H.J. Keum, and K.Y. Han. 2019. Real-time urban inundation prediction combining hydraulic and probabilistic methods. Water 11(2): Article 293.

[15] Krupka M. A rapid inundation flood cell model for flood risk analysis, 2009, Edinburgh, UK: Heriot-Watt University

[16] Lee, J.Y., C. Choi, D. Kang, B.S. Kim, and T.W. Kim. 2020. Estimating design floods at ungauged watersheds in South Korea using machine learning models. Water 12(11): Article 3022.

[17] Lee, J., and B. Kim. 2021. Scenario-based real-time flood prediction with logistic regression. Water 13(9): Article 1191.

[18] Leitao JP, Simoes NE, Maksimovic C, Ferreira F, Prodanovic D, Matos JS, Sa Marques A. Real-time forecasting urban drainage models: Full or simplified networks?. Water Science and Technology, 2010, 62(9): 2106-2114

[19] Li, X.H., and P. Willems. 2020. A hybrid model for fast and probabilistic urban pluvial flood prediction. Water Resources Research 56(6): Article e2019WR025128.

[20] Liu Y, Zhang S, Liu L, Wang X, Huang H. Research on urban flood simulation: A review from the smart city perspective. Progress in Geography, 2015, 34(4): 494-504.

[21] María TC, Jorge G, Cristián E. Forecasting flood hazards in real time: A surrogate model for hydrometeorological events in an Andean watershed. Natural Hazards and Earth System Sciences, 2020, 20(12): 3261-3277

[22] May W. Potential future changes in the characteristics of daily precipitation in Europe simulated by the HIRHAM regional climate model. Climate Dynamics, 2008, 30(6): 581-603

[23] Meng, L., H. Wu, J.X. Wang, and M. Lei. 2009. Application of Elman neural network to width spread prediction in Medium Plate Mill. In Proceedings of the 2009 International Conference on Measuring Technology and Mechatronics Automation, 11–12 April 2009, Zhangjiajie, China:187–190.

[24] Moulin L, Gaume E, Obled C. Uncertainties on mean areal precipitation: Assessment and impact on streamflow simulations. Hydrology and Earth System Sciences, 2009, 13(2): 99-114

[25] Mounce SR, Shepherd W, Sailor G, Shucksmith J, Saul AJ. Predicting combined sewer overflows chamber depth using artificial neural networks with rainfall radar data. Water Science and Technology, 2014, 69(6): 1326-1333

[26] Nash JE, Sutcliffe JV. River flow forecasting through conceptual models part I – A discussion of principles. Journal of Hydrology, 1970, 10(3): 282-290

[27] Rjeily YA, Abbas O, Sadek M, Shahrour I, Chehade FH. Flood forecasting within urban drainage systems using NARX neural network. Water Science and Technology, 2017, 76(9): 2401-2412

[28] Santhi C, Arnold JG, Williams JR, Dugas WA, Srinivasan R, Hauck LM. Validation of the SWAT model on a large river basin with point and nonpoint sources. Journal of the American Water Resources Association, 2010, 37(5): 1169-1188

[29] She L, You XY. A dynamic flow forecast model for urban drainage using the coupled artificial neural network. Water Resources Management, 2019, 33(9): 3143-3153

[30] Wan X, Yang Q, Jiang P, Zhong P. A hybrid model for real-time probabilistic flood forecasting using Elman neural network with heterogeneity of error distributions. Water Resources Management, 2019, 33(11): 4027-4050

[31] Wei M, She L, You XY. Establishment of urban waterlogging pre-warning system based on coupling RBF-NARX neural networks. Water Science and Technology, 2020, 82(9): 1921-1931

[32] Wu, H.C., and G.R. Huang. 2016. Risk assessment of urban waterlogging based on PCSWMM model. Water Resources Protection 32(05): 11–16 (in Chinese).

[33] Wu Z, Zhou Y, Wang H. Real-time prediction of the water accumulation process of urban stormy accumulation points based on deep learning. IEEE Access, 2020, 8: 151938-151951

[34] Yan J, Jin JM, Chen FR, Yu G, Yin HL, Wang WJ. Urban flash flood forecast using support vector machine and numerical simulation. Journal of Hydroinformatics, 2018, 20(1): 221-231

[35] Yin J, Ye M, Yin Z, Xu S. A review of advances in urban flood risk analysis over China. Stochastic Environmental Research and Risk Assessment, 2015, 29: 1063-1070

[36] Zanchetta, A.D.L., and P. Coulibaly. 2020. Recent advances in real-time pluvial flash flood forecasting. Water 12(2): Article 570.

[37] Zeng, Z., Z. Wang, X. Wu, C. Lai, and X. Chen. 2017. Rainstorm waterlogging simulations based on SWMM and LISFLOOD models. Journal of Hydroelectric Engineering 36(5): 68–77 (in Chinese).

[38] Zhang, M., L.F. Zhao, and X. Quan. 2019. Application of Echo State Network in the prediction of water level at urban waterlogging points. China Rural Water and Hydropower (6): 56–59; 65 (in Chinese).

[39] Zhang S, Pan B. An urban storm-inundation simulation method based on GIS. Journal of Hydrology, 2014, 517(5): 260-268

[40] Zheng, S.S., Q. Wan, and M.Y. Jia. 2014. Short-term forecasting of waterlogging at urban storm-waterlogging monitoring sites based on STARMA model. Progress in Geography 33(7): 949–957 (in Chinese).