Abstract
In this research paper, we study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history, leveraging a database of synthetic storm simulations. Traditionally, computational fluid dynamics (CFD) solvers are employed to numerically solve the storm surge governing equations that correspond to expensive to evaluate partial differential equations (PDE). This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations. This model can serve as a fast and affordable emulator for the expensive CFD solvers creating the original database. The neural network model is trained with the storm track parameters used to drive the CFD solvers, and the output of the model is the time-series evolution of the predicted storm surge across multiple nodes within the spatial domain of interest. Once the model is trained, it can be deployed for further predictions based on new storm track inputs. The developed neural network model is a time-series model, composed of a long short-term memory (LSTM), a variation of recurrent neural network (RNN), further enriched with convolutional neural networks (CNNs). The convolutional neural network is employed to capture the correlation of data spatially (across the aforementioned nodes). Therefore, the temporal and spatial correlations of data are captured by the combination of the mentioned models, representing the ConvLSTM model. As the problem is a sequence to sequence time-series problem, an encoder–decoder ConvLSTM model is designed. Furthermore, the performance of the developed convolutional recurrent neural network model is improved by residual connection networks. Additional techniques are employed in the process of model training to enrich the model performance that the model can learn from the data in a more effective way. The performance of the developed model is compared with the results provided by a Gaussian process (GP) implementation, representing a state-of-the-art alternative for establishing time-series emulation of storm surge predictions. The results show that the proposed convolutional recurrent neural network outperforms the GP implementation for the examined synthetic storm database.
Similar content being viewed by others
References
Hallegatte S, Patmore N, Mestre O, Dumas P, Corfee-Morlot J, Herweijer C, Muir-Wood R (2008) Assessing climate change impacts, sea level rise and storm surge risk in port cities: a case study on Copenhagen. OECD Environment Working Papers(3), 0_1,
Luettich RA, Westerink JJ, Scheffner NW (1992) ADCIRC: An advanced three-dimensional circulation model for shelves, coasts, and estuaries. Report 1. Theory and methodology of ADCIRC-2DDI and ADCIRC-3DL. Dredging Research Program Technical Report DRP-92-6, U.S Army Engineers Waterways Experiment Station, Vicksburg, MS,
Westerink J, Luettich R, Feyen J, Atkinson J, Dawson C, Roberts H, Powell M, Dunion J, Kubatko E, Pourtaheri H (2008) A basin- to channel-scale unstructured grid hurricane storm surge model applied to Southern Louisiana. Mon Weather Rev 136:833–864
Booij N, Holthuijsen LH, Ris RC (1996) The SWAN wave model for shallow water. 25th International Conference on Coastal Engineering, Orlando, FL, 668-676,
Smith J. M, Sherlock AR, Resio DT (2001) STWAVE: Steady-state spectral wave model user’s manual for STWAVE, Version 3.0. DTIC Document,
Kyprioti AP, Adeli E, Taflanidis AA, Westerink JJ, Tolman HL (2021) Probabilistic storm surge estimation for landfalling hurricanes: advancements in computational efficiency using quasi-Monte Carlo techniques. J Marine Sci Eng 9(12):1322. https://doi.org/10.3390/jmse9121322
Irish JL, Resio DT, Cialone MA (2009) A surge response function approach to coastal hazard assessment. Part 2: Quantification of spatial attributes of response functions. Natural hazards 51(1):183–205
Jia G, Taflanidis A (2013) Kriging metamodeling for approximation of high-dimensional wave and surge responses in real-time storm/hurricane risk assessment. Comput Methods Appl Mech Eng 261:24–38
Kim S, Melby J, Nadal-Caraballo NC, Ratcli J (2015) A time-dependent surrogate model for storm surge prediction based on an artificial neural network using high-fidelity synthetic hurricane modeling. Nat Hazards 76(1):565–585
Jia G, Taflanidis A, Nadal-Caraballo N, Melby J, Kennedy A, Smith J (2016) Surrogate modeling for peak or time-dependent storm surge prediction over an extended coastal region using an existing database of synthetic storms. Nat Hazards 81:909–938
Al Kajbaf A, Bensi M (2020) Application of surrogate models in estimation of storm surge: A comparative assessment. Applied Soft Computing, 106184,
Contento A, Xu H, Gardoni P (2020) Probabilistic formulation for storm surge predictions. Struct Infrastruct Eng 16(4):547–566
Traffic Flow Prediction for Urban Road Sections Based on Time Series Analysis and LSTM-BILSTM Method. IEEE Transactions on Intelligent Transportation Systems. Volume 23(6), 5615-5624, 2022
Chen X et al (2020) Sensing Data Supported Traffic Flow Prediction via Denoising Schemes and ANN: a comparison. IEEE Sens J 20(23):14317–14328
Xiao G et al. Exploring influence mechanism of bikesharing on the use of public transportation - a case of Shanghai. https://doi.org/10.1080/19427867.2022.209328
Resio D, Westerink J (2008) Modeling the physics of storm surges. Physics Today,
Kijewski-Correa T, Taflanidis A, Vardeman C, Sweet J, Zhang J, Snaiki R, Wu T, Silver Z, Kennedy A (2020) Geospatial environments for hurricane risk assessment: applications to situational awareness and resilience planning in New Jersey. Front Built Environ 6:549106
Nadal-Caraballo NC, Campbell MO, Gonzalez VM, Torres MJ, Melby MJ, Taflanidis AA (2020) Coastal hazards system: a probabilistic coastal hazard analysis framework. J Coastal Res 95(sp1):1211–1216
Toro G, Resio D, Divoky D, Niedoroda A, Reed C (2010) Efficient joint-probability methods for hurricane surge frequency analysis. Ocean Eng 37(1):125–134
Lee J-W, Irish JL, Bensi MT, Marcy DC (2021) Rapid prediction of peak storm surge from tropical cyclone track time series using machine learning. Coast Eng 170:104024
RamosValle AN, Curchitser EN, Bruyere CL, McOwen S (2021) Implementation of an Artificial Neural Network for Storm Surge Forecasting. Journal of Geophysical Research: Atmospheres 126(13):
Kim R, So C, Jeong M, Lee S, Kim J, Kang J (2019) HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction. arXiv preprint arXiv:1908.07999,
Namdari A, Durrani T (2021) HATS: A Multilayer Feedforward Perception Model in Neural Networks for Predicting Stock Market Short-term Trends. Operations Research Forum volume 2, Article number: 38,
Jelesnianski C. P, Chen J, Shaffer W. A (1992) SLOSH: Sea, lake, and overland surges from hurricanes. NOAA Technical Report, NWS 48. US Department of Commerce, National Oceanic and Atmospheric Administration,
Holland GJ (2008) A revised hurricane pressure-wind model. Mon Weather Rev 136(9):3432–3445
Holland GJ, Belanger JI, Fritz A (2010) A revised model for radial profiles of hurricane winds. Mon Weather Rev 138(12):4393–4401
Marks FD (2003) Hurricanes. Handbook of Weather, Climate, and Water: Dynamics, Climate, Physical Meteorology, Weather Systems, and Measurements 641–675
Di Liberto T, Colle BA, Georgas N, Blumberg AF, Taylor AA (2011) Verification of a multimodel storm surge ensemble around New York City and Long Island for the cool season. Weather Forecast 26(6):922–939
Dresback K, Fleming J, Blanton B, Kaiser C, Gourley J, Tromble E, Kolar R, Hong Y, Cooten S, Vergara H, Flamig Z, Lander H, Kelleher K, Nemunaitis-Monroe K (2013) Skill assessment of a real-time forecast system utilizing a coupled hydrologic and coastal hydrodynamic model during Hurricane Irene. Cont Shelf Res 71:78–94
Davis JR, Paramygin VA, Forrest D, Sheng YP (2010) Toward the probabilistic simulation of storm surge and inundation in a limited-resource environment. Mon Wea Rev 138(7):
Bernier NB, Thompson KR (2015) Deterministic and ensemble storm surge prediction for Atlantic Canada with lead times of hours to ten days. Ocean Model 86:114–127
Taylor AA, Glahn B(2008) Probabilistic guidance for hurricane storm surge. 19th Conference on probability and statistics, ,
Lee T (2006) Neural network prediction of a storm surge. Ocean Eng 33:483–494
Lee T (2008) Back-propagation neural network for the prediction of the short-term storm surge in Taichung harbor, Taiwan. Eng Appl Artif Intell 21:63–72
Lee T (2009) Predictions of typhoon storm surge in Taiwan using artificial neural networks. Adv Eng Softw 40:1200–1206
De Oliveira M, Ebecken F, De Oliveira F, de Azevedo Santos I (2009) Neural network model to predict a storm surge. J Appl Meteorol Climatol 48 (1), 143-155,
Bajo M, Umgiesser G (2010) Storm surge forecast through a combination of dynamic and neural network models. Ocean Model 33(1):1–9
Hashemi M, Spaulding M, Shaw A, Farhadi H, Lewis M (2016) An efficient artificial intelligence model for prediction of tropical storm surge. Nat Hazards 82(1):471–491
Kim S, Pan S, Mase H (2019) Artificial neural network-based storm surge forecast model: Practical application to Sakai Minato Japan. Appl Ocean Res 91:101871
Chao W, Young C, Hsu T, Liu W, Liu C (2020) Long-lead-time prediction of storm surge using artificial neural networks and effective typhoon parameters: revisit and deeper insight. Water 2020 12(9):2394
Das H, Jung H, Ebersole B, Wamsley T, Whalin R (2011) An efficient storm surge forecasting tool for coastal Mississippi. Coastal Eng Proceed 1(32):21
Alemany S, Beltran J, Perez A, Ganzfried S Predicting Hurricane Trajectories using a Recurrent Neural Network. arXiv:1802.02548v3
Chen K, Kuang C, Wang L, Chen K, Han X, Fan J (2022) Storm surge prediction based on long short-term memory neural network in the east china sea. Appl. Sci. 2022, 12(1):181
Igarashi Y, Tajima Y (2021) Application of recurrent neural network for prediction of the time-varying storm surge. Coast Eng J 63(1):68–82
Sutskever I, Vinyals O, Le Q (2014) Sequence to sequence learning with neural networks, arXiv preprint arXiv:1409.3215,
Kyprioti A, Irwin C, Taflanidis A, Nadal-Caraballo N, Yawn M, Aucoin L (2023) Spatio-temporal storm surge emulation using Gaussian Process techniques. Coast Eng 180:104231
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Dupond S (2019) A thorough review on the current advance of neural network structures. Annu Rev Control 14:200–230
Shi X, Chen Z, Wang H, Yeung D-Y, Wong W-K, Woo W-C (2015) Convolutional lstm network: a machine learning approach for precipitation nowcasting. Adv Neural Inf Process Syst 28:802–810
Graves A (2013) Generating sequences with recurrent neural networks, arXiv preprint arXiv:1308.0850,
van der Maaten L, Postma E, van den Herik H (2009) Dimensionality reduction: a comparative review. Tilburg University, Tech. rep.
Bengio Y (2009) Learning Deep Architectures for AI. Found Trends Mach Learn 2(1):1–127. https://doi.org/10.1561/2200000006
Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks, in: Advances in neural information processing systems,pages 1097-1105,
Han G, Sun L, Wang J (2021) PhyGeoNet: Physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain. J Comput Phys 428,
Shi W, Caballero J, Huszar F, Totz J, Aitken A. P, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network, In: Proceedings of the IEEE conference on computer vision and pattern recognition, 1874-1883,
Shan Q, Li Z, Jia J, Tang C (2008) Fast image/video upsampling. ACM Trans Graph (TOG) 27(5):1–7
Odena A, Dumoulin V, Olah C (2016) Deconvolution and checkerboard artifacts. Distill 1(10):e3
Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305
Acknowledgements
Authors would like to thank the Army Corp of Engineers, Coastal Hydraulics Laboratory of the Engineering Research and Development Center for providing access to the storm surge data used in the illustrative case study, through the coastal hazards system (https://chs.erdc.dren.mil/).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Test grids
Appendix: Test grids
In this section, the comparison of the prediction by the developed convolutional recurrent neural network and Gaussian process is shown in Figs. 9 and 10. Figure 9 shows the comparison for a grid from the early layers of the coast, and Fig. 10 shows a grid from the last layer of grids in the coast. As it is mentioned in Sect. 4, the results by convolutional recurrent neural network model are much better and more accurate than the Gaussian process.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Adeli, E., Sun, L., Wang, J. et al. An advanced spatio-temporal convolutional recurrent neural network for storm surge predictions. Neural Comput & Applic 35, 18971–18987 (2023). https://doi.org/10.1007/s00521-023-08719-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08719-2