Rapid Simulation of Floods by Considering the Spatial and Temporal Characteristics of Inundation

Abstract

Dike-break floods, characterized by high flood peaks, large volumes, and sudden onsets, seriously threaten the flood control and safety of river basins. In addressing the computationally intensive and time-consuming problem of numerical modeling of large-scale outburst floods, this study proposed a novel hybrid alternative modeling approach. The proposed methodology integrates a low-fidelity (LF) hydrodynamic model with a sparse Gaussian processes (SGP) model, incorporates rotated empirical orthogonal functions (REOF) to address high-dimensional data challenges, streamlines the model structure, and enhances computational efficiency. The SGP model uses training data from the high-fidelity (HF) model to rectify LF model results, enhancing computational efficiency while ensuring precise reproduction of HF model results. Validation in the Yongding River floodplain demonstrates that the hybrid model significantly improves flood extent and depth predictions compared to the LF model, with substantially lower computational costs than the HF model. The results indicate that the REOF-SGP model achieved probability of detection (POD) values higher than 0.8 and rate of false alarm (RFA) values lower than 0.2 within the 120-hour simulation period. The prediction error for inundation depth in the floodplain generally fell within the range of (−0.1 m, 0.1 m). The computational efficiency was 11 times higher than that of the HF hydrodynamic model. This method enhances large-scale flood inundation calculation efficiency while ensuring refined simulation of dynamic flood area changes, aiding rapid prediction of nonlinear flood evolution and water depth distribution.

Keywords

Computational efficiency / Dike-break floods / REOF / SGP / Yongding river floodplain

References

[1] BaldwinMP, StephensonDB, JolliffeLT. Spatial weighting and iterative projection methods for EOFs. Journal of Climate, 2009, 22(2): 234-243

[2] BalicaSF, PopescuI, BeeversL, WrightNG. Parametric and physically based modelling techniques for flood risk and vulnerability assessment: A comparison. Environmental Modelling and Software, 2013, 41: 84-92

[3] Bandara, K., C. Bergmeir, and S. Smyl. 2020. Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach. Expert Systems With Applications 140: Article 112896.

[4] Bauer, M., M.V.D. Wilk, and C.E. Rasmussen. 2016. Understanding probabilistic sparse Gaussian process approximations. arXiv: 1606.04820

[5] BerniniA, FranchiniM. A rapid model for delimiting flooded areas. Water Resources Management, 2013, 27(10): 3825-3846

[6] BoH, LinQ, LiL, WeiC, GongC. Accuracy evaluation of two satellite precipitation products (lMERG and MSWEP) at precipitation zoning scale based on REOF in the Jinsha River Basin. Journal of Lake Sciences, 2024, 36(2): 620-634

[7] Burt, D.R., C.E. Rasmussen, and M. van der Wilk. 2019. Rates of convergence for sparse variational Gaussian process Regression. arXiv: 1903.03571.

[8] Chang, C.H., H. Lee, S.K. Do, T.L.T. Du, K. Markert, F. Hossain, S.K. Ahmad, T. Piman, et al. 2023. Operational forecasting inundation extents using REOF analysis (FIER) over lower Mekong and its potential economic impact on agriculture. Environmental Modelling and Software 162: Article 105643.

[9] ClementE, LawKJH, WadeS, ZankinV. Fast deep mixtures of Gaussian process experts. Machine Learning, 2024, 113(3): 1483-1508

[10] DavidsenS, LöweR, ThrysøeC, Arnbjerg-NielsenK. Simplification of one-dimensional hydraulic networks by automated processes evaluated on 1D/2D deterministic flood models. Journal of Hydroinformatics, 2017, 19(5): 686-700

[11] DonatR, MartíMC, GavaraAM, MuletP. Well-balanced adaptive mesh refinement for shallow water flows. Journal of Computational Physics, 2014, 257: 937-953

[12] DoricaM, GiannacopoulosDD. Response surface space mapping for electromagnetic optimization. IEEE Transactions on Magnetics, 2006, 42(4): 1123-1126

[13] FerrariA, DazziS, VacondioR, MignosaP. Enhancing the resilience to flooding induced by levee breaches in lowland areas: A methodology based on numerical modelling. Natural Hazards and Earth System Sciences, 2020, 20(1): 59-72

[14] FraehrN, WangQJ, WuW, NathanR. Development of a fast and accurate hybrid model for floodplain inundation simulations. Water Resources Research, 2023

[15] HachinoT, KadirkamanathanV. Multiple Gaussian process models for direct time series forecasting. IEEJ Transactions on Electrical and Electronic Engineering, 2011, 6(3): 245-252

[16] He, D., S. Sun, and L. Xie. 2024. Multi-target feature selection with subspace learning and manifold regularization. Neurocomputing 582: Article 127533.

[17] Hernández M.M., M.B. Sharif, A. Kalyanapu, S.K. Ghafoor, T.T. Dullo, S. Gangrade, S.C. Kao, M.R. Norman, and K.J. Evans. 2021. TRITON: A multi-GPU open source 2D hydrodynamic flood model. Environmental Modelling & Software 141: Article 105034.

[18] HuR, FangF, PainCC, NavonIM. Rapid spatio-temporal flood prediction and uncertainty quantification using a deep learning method. Journal of Hydrology, 2019, 575: 911-920

[19] HuangG, ChenZ, ZengB. Research progress of urban flood model and CPU-GPU heterogeneous parallel computing technology. Journal of Hydraulic Engineering, 2023, 54(6): 654-665

[20] HumphreyGB, MaierHR, WuW, MountNJ, DandyGC, AbrahartRJ, DawsonCW. Improved validation framework and R-package for artificial neural network models. Environmental Modelling and Software, 2017, 92: 82-106

[21] Ian, T.J., and C. Jorge. 2016. Principal component analysis: A review and recent developments. Philosophical Transactions Series A, Mathematical, Physical, and Engineering Sciences 374(2065): Article 20150202.

[22] JamaliB, BachPM, CunninghamL, DeleticA. A cellular automata fast flood evaluation (CA-ffe) model. Water Resources Research, 2019, 55(6): 4936-4953

[23] JianD, XuQ, SongS. Adaptive physical-constraints-preserving unstaggered central schemes for shallow water equations on quadrilateral meshes. ESAIM: Mathematical Modelling and Numerical Analysis, 2022, 56(6): 2297-2338

[24] JinH, ZhaoY, LuP, ZhangS, ChenY, ZhengS, ZhuZ. Using machine learning to identify and optimize sensitive parameters in urban flood model considering subsurface characteristics. International Journal of Disaster Risk Science, 2024, 15(1): 116-133

[25] Kabir, S., S. Patidar, and G. Pender. 2020. A machine learning approach for forecasting and visualizing flood inundation information. Proceedings of the Institution of Civil Engineers – Water Management 174(1): 1–29.

[26] Leibfried, F., V. Dutordoir, S.T. John, and N. Durrande. 2020. A tutorial on sparse Gaussian processes and variational inference. arXiv: 2012.13962.

[27] LiD, WangX, ZhaoM, ZhangJ, LiuS, LiuJ. Flood dispatching numerical simulation for detention basins of Yongding River. Journal of Tianjin University (Science and Technology), 2015, 48(1): 76-86

[28] LiJ, ZhangX, ZhouT, WeiZ, LiX. Application of Beijing series high-resolution satellites in flood analysis of the Yongding River Basin. China Water Resources, 2024, 3: 69-72

[29] LiuY, LiuY, ZhengJ, ChaiF, LiM, MuJ. Intelligent rapid prediction method of urban flooding based on BP neural network and numerical simulation model. Journal of Hydraulic Engineering, 2022, 53(3): 284-295

[30] McGrathH, BourgonJF, Proulx-BourqueJS, NastevM, EzzAAE. A comparison of simplified conceptual models for rapid web-based flood inundation mapping. Natural Hazards, 2018, 93(2): 905-920

[31] MiaoY. Full waveform inversion in time domain based on limited-memory BFGS algorithm. Oil Geophysical Prospecting, 2015, 50(3): 469-474

[32] Niroshinie, M.A.C., and N. Yasuo. 2016. Flood inundation modelling considering the effect of debris blockage in bridges. Paper presented at IAHR APD 2016, 20–23 November 2016, Bali, Indonesia.

[33] NocedalJ. Updating quasi-Newton matrices with limited storage. Mathematics of Computation, 1980, 35(151): 773-782

[34] ParkerK, RuggieroP, SerafinKA, HillDF. Emulation as an approach for rapid estuarine modeling. Coastal Engineering, 2019, 150: 79-93

[35] PierfrancoC, CostanzoC, MacchioneF. Performances and limitations of the diffusive approximation of the 2-D shallow water equations for flood simulation in urban and rural areas. Applied Numerical Mathematics, 2016, 116: 141-156

[36] PrestininziP. Suitability of the diffusive model for dam break simulation: Application to a CADAM experiment. Journal of Hydrology, 2008, 361(1): 172-185

[37] Qian, K., A. Mohamed, and C. Claudel. 2019. Physics informed data driven model for flood prediction: Application of deep learning in prediction of urban flood development. arXiv: 1908.10312.

[38] QiaoJ, HanR, YangJ, YangX, WangZ, YangB Investigation and analysis of the extraordinary flood in the Haihe River Basin during July 2023, 2024 Beijing China Water and Power Press

[39] RazaviS, TolsonBA, BurnDH. Review of surrogate modeling in water resources. Water Resources Research, 2012

[40] RobertoB, ElvinI, NicolaasJS, RiccardoT. Deep learning methods for flood mapping: A review of existing applications and future research directions. Hydrology and Earth System Sciences, 2022, 26(16): 4345-4378

[41] SavageJTS, BatesP, FreerJ, NealJ, AronicaG. When does spatial resolution become spurious in probabilistic flood inundation predictions?. Hydrological Processes, 2016, 30(13): 2014-2032

[42] Shuai, X., W. Wu, M. Sebastian, Q. Wang, N. Rory, and Y. Huang. 2020. Artificial neural network based hybrid modeling approach for flood inundation modeling. Journal of Hydrology 592: Article 125605.

[43] SunG, LiG, StoneM, LiQ. A two-stage multi-fidelity optimization procedure for honeycomb-type cellular materials. Computational Materials Science, 2010, 49(3): 500-511

[44] WanH, NiY. Bayesian modeling approach for forecast of structural stress response using structural health monitoring data. Journal of Structural Engineering, 2018

[45] WeiF Modern climatic statistical diagnosis and prediction technology, 1999 Beijing China Meteorological Press

[46] YannL, YoshuaB, GeoffreyH. Deep learning. Nature, 2015, 521(7553): 436-444

[47] YuanX, TianF, WangL. Comprehensive two-dimensional associate hydrodynamic models for overflow and levee-breach flood and its application. Advances in Water Science, 2015, 26(1): 83-90

[48] Zahura, F.T., J.L. Goodall, J.M. Sadler, Y. Shen, M.M. Morsy, and M. Behl. 2020. Training machine learning surrogate models from a high-fidelity physics-based model: Application for real-time street-scale flood prediction in an urban coastal community. Water Resources Research 56(10): Article e2019WR027038.

[49] Zhou, Y, W. Wu, R. Nathan, and Q. Wang. 2021. A rapid flood inundation modelling framework using deep learning with spatial reduction and reconstruction. Environmental Modelling and Software 143: Article 105112.

RIGHTS & PERMISSIONS

The Author(s)