Identifying the Sensitivity of Ensemble Streamflow Prediction by Artificial Intelligence

Sustainable water resources management is facing a rigorous challenge due to global climate change. Nowadays, improving streamflow predictions based on uneven precipitation is an important task. The main purpose of this study is to integrate the ensemble technique concept into artificial neural networks for reducing model uncertainty in hourly streamflow predictions. The ensemble streamflow predictions are built following two steps: (1) Generating the ensemble members through disturbance of initial weights, data resampling, and alteration of model structure; (2) consolidating the model outputs through the arithmetic average, stacking, and Bayesian model average. This study investigates various ensemble strategies on two study sites, where the watershed size and hydrological conditions are different. The results help to realize whether the ensemble methods are sensitive to hydrological or physiographical conditions. Additionally, the applicability and availability of the ensemble strategies can be easily evaluated in this study. Among various ensemble strategies, the best ESP is produced by the combination of boosting (data resampling) and Bayesian model average. The results demonstrate that the ensemble neural networks greatly improved the accuracy of streamflow predictions as compared to a single neural network, and the improvement made by the ensemble neural network is about 19–37% and 20–30% in Longquan Creek and Jinhua River watersheds, respectively, for 1–3 h ahead streamflow prediction. Moreover, the results obtained from different ensemble strategies are quite consistent in both watersheds, indicating that the ensemble strategies are insensitive to hydrological and physiographical factors. Finally, the output intervals of ensemble streamflow prediction may also reflect the possible peak flow, which is valuable information for flood prevention.

[1]  Edward E. Leamer,et al.  Specification Searches: Ad Hoc Inference with Nonexperimental Data , 1980 .

[2]  Vijay P. Singh,et al.  A general framework for multivariate multi-index drought prediction based on Multivariate Ensemble Streamflow Prediction (MESP) , 2016 .

[3]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[4]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[5]  Taha B. M. J. Ouarda,et al.  Comparison of ice-affected streamflow estimates computed using artificial neural networks and multiple regression techniques , 2008 .

[6]  Shahab Araghinejad,et al.  Application of artificial neural network ensembles in probabilistic hydrological forecasting , 2011 .

[7]  K. Pearson.  VII. Note on regression and inheritance in the case of two parents , 1895, Proceedings of the Royal Society of London.

[8]  X. Yin,et al.  A reservoir operating method for riverine ecosystem protection, reservoir sedimentation control and water supply , 2014 .

[9]  Yen-Ming Chiang,et al.  Evaluating the contribution of multi-model combination to streamflow hindcasting by empirical and conceptual models , 2017 .

[10]  F. Chang,et al.  Exploring the Mechanism of Surface and Ground Water through Data-Driven Techniques with Sensitivity Analysis for Water Resources Management , 2016, Water Resources Management.

[11]  Lihua Xiong,et al.  Indices for assessing the prediction bounds of hydrological models and application by generalised likelihood uncertainty estimation / Indices pour évaluer les bornes de prévision de modèles hydrologiques et mise en œuvre pour une estimation d'incertitude par vraisemblance généralisée , 2009 .

[12]  Ahmed El-Shafie,et al.  Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure , 2014, Water Resources Management.

[13]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.

[14]  T. Ouarda,et al.  Flood frequency analysis at ungauged sites using artificial neural networks in canonical correlation analysis physiographic space , 2007 .

[15]  Huan Wang,et al.  A Comparative Study of Artificial Neural Networks, Support Vector Machines and Adaptive Neuro Fuzzy Inference System for Forecasting Groundwater Levels near Lake Okeechobee, Florida , 2015, Water Resources Management.

[16]  C. M. DeChant,et al.  Improving the characterization of initial condition for ensemble streamflow prediction using data assimilation , 2011 .

[17]  Y. Yoshida,et al.  Downscaling medium-range ensemble forecasts using a neural network approach , 2015 .

[18]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[19]  Fi-John Chang,et al.  A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques , 2016 .

[20]  Bithin Datta,et al.  Stochastic and Robust Multi-Objective Optimal Management of Pumping from Coastal Aquifers Under Parameter Uncertainty , 2014, Water Resources Management.

[21]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[22]  Vinay Kumar Deolia,et al.  Neural Network Based Sliding Mode Control for Uncertain Discrete-Time Nonlinear Systems with Time-Varying Delay , 2016 .

[23]  J. Adamowski,et al.  Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models , 2015, Hydrogeology Journal.

[24]  Jery R. Stedinger,et al.  Reservoir optimization using sampling SDP with ensemble streamflow prediction (ESP) forecasts , 2001 .

[25]  Chandranath Chatterjee,et al.  Uncertainty assessment and ensemble flood forecasting using bootstrap based artificial neural networks (BANNs) , 2010 .

[26]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[27]  K. Abbaspour,et al.  Estimating Uncertain Flow and Transport Parameters Using a Sequential Uncertainty Fitting Procedure , 2004 .

[28]  Saumen Maiti,et al.  A comparative study of artificial neural networks, Bayesian neural networks and adaptive neuro-fuzzy inference system in groundwater level prediction , 2014, Environmental Earth Sciences.

[29]  K. Sudheer,et al.  Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations , 2013 .

[30]  Jan Seibert,et al.  On the need for benchmarks in hydrological modelling , 2001 .

[31]  Vinay Kumar Deolia,et al.  Stabilization of Unknown Nonlinear Discrete-Time Delay Systems Based on Neural Network , 2012 .

[32]  Edwin E. Herricks,et al.  AI techniques for optimizing multi-objective reservoir operation upon human and riverine ecosystem demands , 2015 .

[33]  C. Shu,et al.  Regional low‐flow frequency analysis using single and ensemble artificial neural networks , 2009 .

[34]  Adrian E. Raftery,et al.  Bayesian model averaging: a tutorial (with comments by M. Clyde, David Draper and E. I. George, and a rejoinder by the authors , 1999 .

[35]  Jan Adamowski,et al.  Urban water demand forecasting and uncertainty assessment using ensemble wavelet‐bootstrap‐neural network models , 2013 .