Abstract
Full process-based hydrodynamic models allows reproducing with high fidelity the complexity of cyclone-induced wave dynamics and their potential impact regarding overtopping-induced inundation. Yet, their major drawback is the high computational time cost (typically of several hours), which prevents them from a direct integration in a real-time early-warning system to support crisis/emergency management. A possible alternative relies on the statistical exploitation of pre-calculated simulation results to build a fast (low computation time cost) prediction model given the offshore conditions (wave and sea level). In the present study, we present a suite of random forest (RF) techniques for fast prediction of key indicators to support forecasting of cyclone-induced wave overtopping, namely: (1) the occurrence likelihood of the overtopping event using a RF-based classification method; (2) the maximum cumulative volume overtopping using a RF-based regression method; (3) the starting time of the overtopping event (referred to as time-to-event) using a multi-output RF-based classification method. We apply the technique at Sainte-Suzanne city at Reunion Island (Indian Ocean basin) using a database of simulation results, which relates offshore conditions (wave and sea level) induced by ~500 synthetic cyclones and their consequences in terms of wave overtopping, namely the time evolution of the cumulative overtopping volume in the vicinity of the emergency center. Through an extensive cross-validation exercise, we show the high performance of the RF models with respect to the prediction of the three indicators. More specifically, the accuracy and the area under the ROC curve (AUC) of the RF-based classifier reaches values above 95%; the R-squared of the RF-based regression model reaches values above 80%; the time-averaged accuracy of the multi-output RF-based classifier reaches values above 80%. As a complementary analysis, the comparison to simulated historical cases (Dumile in 2013, and Dina in 2002) shows error less than 10% on flooding indicators 2 and 3. Finally, we take advantage of the probabilistic information provided by RF models to evaluate some measure of confidence associated to the prediction result.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertin X (2016) Storm surges and coastal flooding: status and challenges. La Houille Blanche - Revue internationale de l’eau, EDP Sciences, pp 64–70
Bonnardot F, Quetelard H, Jumaux G, Leroux MD, Bessafi M (2018) Probabilistic forecasts of tropical cyclone tracks and intensities in the Southwest Indian Ocean Basin. Q J R Meteorol Soc 145(719):675–686
Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30(7):1145–1159
Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. Chapman and Hall/CRC, New York
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Cheung KF, Phadke AC, Wei Y, Rojas R, Douyere YJM, Martino CD, Houston SH, Liu PLF, Lynett PJ, Dodd N, Liao S, Nakazaki E (2003) Modeling of storm-induced coastal flooding for emergency management. Ocean Eng 30(11):1353–1386
Deb M, Ferreira CM (2018) Simulation of cyclone-induced storm surges in the low-lying delta of Bangladesh using coupled hydrodynamic and wave model (SWAN + ADCIRC). J Flood Risk Manag 11:750–765
Diamond HJ, Lorrey AM, Knapp KR, Levinson DH (2012) Development of an enhanced tropical cyclone tracks database for the Southwest Pacific from 1840 to 2010. Int J Climatol 32(14):2240–2250
EurOtop (2016) Manual on wave overtopping of sea defences and related structures. An overtopping manual largely based on European research, but for worldwide application. In: Van der Meer JW, Allsop NWH, Bruce T, De Rouck J, Kortenhaus A, Pullen T, Schüttrumpf H, Troch P, Zanuttigh B (eds). www.overtopping-manual.com
Glahn B, Taylor A, Kurkowski N, Shaffer WA (2009) The role of the SLOSH model in national weather service storm surge forecasting. Natl Weather Dig 33(1):3–14
Hashemi MR, Spaulding ML, Shaw A, Farhadi H, Lewis M (2016) An efficient artificial intelligence model for prediction of tropical storm surge. Nat Hazards 82(1):471–491
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New York
Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, New York
Lecacheux S, Pedreros R, Le Cozannet G, Thiébot J, De La Torre Y, Bulteau T (2012) A method to characterize the different extreme waves for islands exposed to various wave regimes: a case study devoted to Reunion Island. Nat Hazards Earth Syst Sci 12:2425–2437
Lecacheux S, Pedreros R, Paris F, Chateauminois E, Nicolae Lerma A, et al. (2016) Toward the implementation of a cyclone-induced coastal hydrodynamics and marine inundation forecasting system for Reunion Island. In: Vila-Concejo A, Bruce E, Kennedy DM, McCarroll RJ (eds) Proceedings of the 14th International Coastal Symposium, Sydney, Australia, March 2016. Journal of Coastal Research, Special Issue, vol 75
Malley JD, Kruppa J, Dasgupta A, Malley KG, Ziegler A (2012) Probability machines: consistent probability estimation using nonparametric learning machines. Methods Inf Med 51(1):74
Meinshausen N (2006) Quantile regression forests. J Mach Learn Res 7:983–999
Paris F, Lecacheux S, Pedreros R, Rohmer J, Sauvagnargues S, Ayral P-A, Tena-Chollet F, Bonnardot F, Quetelard H (2019) A framework to design a GIS-based decision support tool for cyclone-induced marine flooding emergency management at Reunion Island. In: SimHydro 2019, 12–14 June 2019, Sophia Antipolis, France
Poelhekke L, Jäger WS, van Dongeren A, Plomaritis TA, McCall R, Ferreira Ó (2016) Predicting coastal hazards for sandy coasts with a Bayesian Network. Coast Eng 118:21–34
Rohmer J, Lecacheux S, Pedreros R, Quetelard H, Bonnardot F, Idier D (2016) Dynamic parameter sensitivity in numerical modelling of cyclone-induced waves: a multi-look approach using advanced meta-modelling techniques. Nat Hazards 84(3):1765–1792
Tang F, Ishwaran H (2017) Random forest missing data algorithms. Stat Anal Data Min: ASA Data Sci J 10(6):363–377
Verhaeghe H, De Rouck J, van der Meer J (2008) Combined classifier–quantifier model: a 2-phases neural model for prediction of wave overtopping at coastal structures. Coast Eng 55(5):357–374
Zanuttigh B, Formentin SM, van der Meer JW (2016) Prediction of extreme and tolerable wave overtopping discharges through an advanced neural network. Ocean Eng 127:7–22
Zijlema M, Stelling G, Smit P (2011) SWASH: an operational public domain code for simulating wave fields and rapidly varied flows in coastal waters. Coast Eng 58(10):992–1012
Acknowledgements
This work is supported by the French National Research Agency within the SPICy project (ANR–14–CE03–0013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Rohmer, J., Lecacheux, S., Pedreros, R., Idier, D., Bonnardot, F. (2020). Early-Warning System for Cyclone-Induced Wave Overtopping Aided by a Suite of Random Forest Approaches. In: Gourbesville, P., Caignaert, G. (eds) Advances in Hydroinformatics. Springer Water. Springer, Singapore. https://doi.org/10.1007/978-981-15-5436-0_35
Download citation
DOI: https://doi.org/10.1007/978-981-15-5436-0_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5435-3
Online ISBN: 978-981-15-5436-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)