Variational Bayesian Neural Network for Ensemble Flood Forecasting

Disastrous floods are destructive and likely to cause widespread economic losses. An understanding of flood forecasting and its potential forecast uncertainty is essential for water resource managers. Reliable forecasting may provide future streamflow information to assist in an assessment of the benefits of reservoirs and the risk of flood disasters. However, deterministic forecasting models are not able to provide forecast uncertainty information. To quantify the forecast uncertainty, a variational Bayesian neural network (VBNN) model for ensemble flood forecasting is proposed in this study. In VBNN, the posterior distribution is approximated by the variational distribution, which can avoid the heavy computational costs in the traditional Bayesian neural network. To transform the model parameters’ uncertainty into the model output uncertainty, a Monte Carlo sample is applied to give ensemble forecast results. The proposed method is verified by a flood forecasting case study on the upper Yangtze River. A point forecasting model neural network and two probabilistic forecasting models, including hidden Markov Model and Gaussian process regression, are also applied to compare with the proposed model. The experimental results show that the VBNN performs better than other comparable models in terms of both accuracy and reliability. Finally, the result of uncertainty estimation shows that the VBNN can effectively handle heteroscedastic flood streamflow data.

[1]  Alexander Y. Sun,et al.  Monthly streamflow forecasting using Gaussian Process Regression , 2014 .

[2]  Kwok-Wing Chau,et al.  ANN-based interval forecasting of streamflow discharges using the LUBE method and MOFIPS , 2015, Eng. Appl. Artif. Intell..

[3]  Guoxiong Wu,et al.  Global risks: Pool knowledge to stem losses from disasters , 2015, Nature.

[4]  Amir F. Atiya,et al.  Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals , 2011, IEEE Transactions on Neural Networks.

[5]  Jianzhong Zhou,et al.  Probabilistic spatiotemporal wind speed forecasting based on a variational Bayesian deep learning model , 2020 .

[6]  Yen-Ming Chiang,et al.  Comparison of static-feedforward and dynamic-feedback neural networks for rainfall -runoff modeling , 2004 .

[7]  Lu Chen,et al.  Efficient estimation of flood forecast prediction intervals via single‐ and multi‐objective versions of the LUBE method , 2016 .

[8]  H. Hersbach Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems , 2000 .

[9]  Florian Pappenberger,et al.  Ensemble flood forecasting: a review. , 2009 .

[10]  Quan J. Wang,et al.  A Bayesian joint probability modeling approach for seasonal forecasting of streamflows at multiple sites , 2009 .

[11]  Rob J Hyndman,et al.  25 years of time series forecasting , 2006 .

[12]  J. Salas,et al.  SHORT‐TERM FORECASTING OF SNOWMELT RUNOFF USING ARMAX MODELS1 , 1988 .

[13]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[14]  James C. Bennett,et al.  Improving Precipitation Forecasts by Generating Ensembles through Postprocessing , 2015 .

[15]  Jose D. Salas,et al.  APPROACHES TO MULTIVARIATE MODELING OF WATER RESOURCES TIME SERIES1 , 1985 .

[16]  K. Chau,et al.  Predicting monthly streamflow using data‐driven models coupled with data‐preprocessing techniques , 2009 .

[17]  Lei Ye,et al.  Multi-objective optimization for construction of prediction interval of hydrological models based on ensemble simulations , 2014 .

[18]  Jie Li,et al.  Deriving reservoir operation rule based on Bayesian deep learning method considering multiple uncertainties , 2019 .

[19]  M. Castellano-Méndez,et al.  Modelling of the monthly and daily behaviour of the runoff of the Xallas river using Box-Jenkins and neural networks methods , 2004 .

[20]  Dimitri P. Solomatine,et al.  Model Induction with Support Vector Machines: Introduction and Applications , 2001 .

[21]  Duan Chen,et al.  Hierarchical Flood Operation Rules Optimization Using Multi-Objective Cultured Evolutionary Algorithm Based on Decomposition , 2018, Water Resources Management.

[22]  Indrajeet Chaubey,et al.  Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed , 2008 .

[23]  Q. J. Wang,et al.  Multisite probabilistic forecasting of seasonal flows for streams with zero value occurrences , 2011 .

[24]  Quan J. Wang,et al.  Ensemble forecasting of sub-seasonal to seasonal streamflow by a Bayesian joint probability modelling approach , 2016 .

[25]  Stefania Tamea,et al.  Verification tools for probabilistic forecasts of continuous hydrological variables , 2006 .

[26]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[27]  Hui Qin,et al.  Monthly streamflow forecasting based on hidden Markov model and Gaussian Mixture Regression , 2018, Journal of Hydrology.