A Data-Driven Probabilistic Rainfall-Inundation Model for Flash-Flood Warnings

Owing to their short duration and high intensity, flash floods are among the most devastating natural disasters in metropolises. The existing warning tools—flood potential maps and two-dimensional numerical models—are disadvantaged by time-consuming computation and complex model calibration. This study develops a data-driven, probabilistic rainfall-inundation model for flash-flood warnings. Applying a modified support vector machine (SVM) to limited flood information, the model provides probabilistic outputs, which are superior to the Boolean functions of the traditional rainfall-flood threshold method. The probabilistic SVM-based model is based on a data preprocessing framework that identifies the expected durations of hazardous rainfalls via rainfall pattern analysis, ensuring satisfactory training data, and optimal rainfall thresholds for validating the input/output data. The proposed model was implemented in 12 flash-flooded districts of the Xindian River. It was found that (1) hydrological rainfall pattern analysis improves the hazardous event identification (used for configuring the input layer of the SVM); (2) brief hazardous events are more critical than longer-lasting events; and (3) the SVM model exports the probability of flash flooding 1 to 3 h in advance.

[1]  Matjaž Mikoš,et al.  Copula-based IDF curves and empirical rainfall thresholds for flash floods and rainfall-induced landslides , 2016 .

[2]  Dawen Yang,et al.  Establishing a rainfall threshold for flash flood warnings in China’s mountainous areas based on a distributed hydrological model , 2016 .

[3]  Reza Maknoon,et al.  Probabilistic rainfall thresholds for flood forecasting: evaluating different methodologies for modelling rainfall spatial correlation (or dependence) , 2011 .

[4]  J. M. Shepherd,et al.  Effect of urbanization on the diurnal rainfall pattern in Houston , 2005 .

[5]  Ezio Todini,et al.  A model conditional processor to assess predictive uncertainty in flood forecasting , 2008 .

[6]  Jie Yin,et al.  Evaluating the impact and risk of pluvial flash flood on intra-urban road network: A case study in the city center of Shanghai, China , 2016 .

[7]  Yang Hong,et al.  A method for probabilistic flash flood forecasting , 2016 .

[8]  Chjeng-Lun Shieh,et al.  Variability in rainfall threshold for debris flow after the Chi-Chi earthquake in central Taiwan, China , 2009 .

[9]  Hélène Roux,et al.  Accounting for rainfall systematic spatial variability in flash flood forecasting , 2016 .

[10]  Suraje Dessai,et al.  Challenges in using probabilistic climate change information for impact assessments: an example from the water sector , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[11]  Reza Khanbilvardi,et al.  Evaluation of Operational National Weather Service Gridded Flash Flood Guidance over the Arkansas Red River Basin , 2013 .

[12]  Sheng-Chi Yang,et al.  Flash flood warnings using the ensemble precipitation forecasting technique: A case study on forecasting floods in Taiwan caused by typhoons , 2015 .

[13]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[14]  Giuseppe T. Aronica,et al.  Rainfall thresholds derivation for warning pluvial flooding risk in urbanised areas , 2016 .

[15]  H. Wheater,et al.  The significance of spatial rainfall representation for flood runoff estimation : A numerical evaluation based on the Lee catchment, UK , 2006 .

[16]  Jihn-Sung Lai,et al.  Coupling typhoon rainfall forecasting with overland-flow modeling for early warning of inundation , 2012, Natural Hazards.

[17]  Yang Hong,et al.  CONUS-Wide Evaluation of National Weather Service Flash Flood Guidance Products , 2014 .

[18]  Jihn-Sung Lai,et al.  Using Tabu Search Adjusted with Urban Sewer Flood Simulation to Improve Pluvial Flood Warning via Rainfall Thresholds , 2019, Water.

[19]  Giorgio Boni,et al.  A hydrometeorological approach for probabilistic flood forecast , 2005 .

[20]  Patrick Arnaud,et al.  Influence of rainfall spatial variability on flood prediction , 2002 .

[21]  Roman Krzysztofowicz,et al.  Bayesian theory of probabilistic forecasting via deterministic hydrologic model , 1999 .

[22]  Florian Pappenberger,et al.  New dimensions in early flood warning across the globe using grand‐ensemble weather predictions , 2008 .

[23]  Leonardo Noto,et al.  Derivation of Rainfall Thresholds for Flash Flood Warning in a Sicilian Basin Using a Hydrological Model , 2016 .

[24]  M. Diakakis.  Rainfall thresholds for flood triggering. The case of Marathonas in Greece , 2011, Natural Hazards.

[25]  M. Borga,et al.  Flash flood warning based on rainfall thresholds and soil moisture conditions: An assessment for gauged and ungauged basins , 2008 .

[26]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[27]  Jihn-Sung Lai,et al.  Improvement of Statistical Typhoon Rainfall Forecasting with ANN-Based Southwest Monsoon Enhancement , 2011 .

[28]  A. Brath,et al.  A stochastic approach for assessing the uncertainty of rainfall‐runoff simulations , 2004 .

[29]  Florian Pappenberger,et al.  Probabilistic flood forecasting and decision-making: an innovative risk-based approach , 2012, Natural Hazards.

[30]  Francesco Marra,et al.  Space–time organization of debris flows-triggering rainfall and its effect on the identification of the rainfall threshold relationship , 2016 .

[31]  Hui-Chung Yeh,et al.  A SCALE‐INVARIANT GAUSS‐MARKOV MODEL FOR DESIGN STORM HYETOGRAPHS1 , 2001 .

[32]  Florian Pappenberger,et al.  The Monetary Benefit of Early Flood Warnings in Europe , 2015 .

[33]  Yang Hong,et al.  Evaluation of Tools Used for Monitoring and Forecasting Flash Floods in the United States , 2012 .

[34]  J. S. Verkade,et al.  Estimating the benefits of single value and probability forecasting for flood warning , 2011 .

[35]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[36]  Maria-Helena Ramos,et al.  Willingness-to-pay for a probabilistic flood forecast: a risk-based decision-making game , 2016 .

[37]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[38]  Colin ClarkCHRS Shute Lane,et al.  Saving Lives: Timely Flash Flood Warnings in the UK , 2017 .

[39]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[40]  Roberto Buizza,et al.  The value of probabilistic prediction , 2008 .

[41]  Caleb A. Buahin,et al.  Probabilistic Flood Inundation Forecasting Using Rating Curve Libraries , 2017 .

[42]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[43]  E. Todini,et al.  Comparing Hydrological Postprocessors Including Ensemble Predictions Into Full Predictive Probability Distribution of Streamflow , 2018, Water Resources Research.

[44]  L. Alfieri,et al.  Flash flood detection through a multi-stage probabilistic warning system for heavy precipitation events , 2011 .