Discrete wavelet transform coupled with ANN for daily discharge forecasting into Três Marias reservoir

Abstract. This paper proposes the use of discrete wavelet transform (DWT) to remove the high-frequency components (details) of an original signal, because the noises generally present in time series (e.g. streamflow records) may influence the prediction quality. Cleaner signals could then be used as inputs to an artificial neural network (ANN) in order to improve the model performance of daily discharge forecasting. Wavelet analysis provides useful decompositions of original time series in high and low frequency components. The present application uses the Coiflet wavelets to decompose hydrological data, as there have been few reports in the literature. Finally, the proposed technique is tested using the inflow records to the Tres Marias reservoir in Sao Francisco River basin, Brazil. This transformed signal is used as input for an ANN model to forecast inflows seven days ahead, and the error RMSE decreased by more than 50% (i.e. from 454.2828 to 200.0483).

[1]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[3]  Francesco Serinaldi,et al.  Impact of EMD decomposition and random initialisation of weights in ANN hindcasting of daily stream flow series: An empirical examination , 2011 .

[4]  A. Heppenstall,et al.  Timing error correction procedure applied to neural network rainfall—runoff modelling , 2007 .

[5]  Celso Augusto Guimarães Santos,et al.  Drought forecast using an artificial neural network for three hydrological zones in San Francisco River basin, Brazil. , 2009 .

[6]  R. Wilby,et al.  A comparison of artificial neural networks used for river forecasting , 1999 .

[7]  Richard Labib,et al.  Performance of Neural Networks in Daily Streamflow Forecasting , 2002 .

[8]  Ozgur Kisi,et al.  Streamflow Forecasting Using Different Artificial Neural Network Algorithms , 2007 .

[9]  C. L. Wu,et al.  Methods to improve neural network performance in daily flows prediction , 2009 .

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[11]  Gustavo Barbosa Lima da Silva,et al.  Daily streamflow forecasting using a wavelet transform and artificial neural network hybrid models , 2014 .

[12]  Robert J. Abrahart,et al.  HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts , 2007, Environ. Model. Softw..

[13]  Camilo Allyson Simões De Farias,et al.  Daily reservoir operating rules by implicit stochastic optimization and artificial neural networks in a semi-arid land of Brazil , 2011 .

[14]  Donna M. Rizzo,et al.  Advances in ungauged streamflow prediction using artificial neural networks , 2010 .

[15]  Wensheng Wang,et al.  Wavelet Transform Method for Synthetic Generation of Daily Streamflow , 2011 .

[16]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[17]  J. Adamowski.  Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis , 2008 .

[18]  F. Anctil,et al.  An exploration of artificial neural network rainfall-runoff forecasting combined with wavelet decomposition , 2004 .

[19]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[20]  Ozgur Kisi,et al.  Stream flow forecasting using neuro‐wavelet technique , 2008 .

[21]  Jan Adamowski,et al.  Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. , 2010 .

[22]  J. Adamowski.  River flow forecasting using wavelet and cross‐wavelet transform models , 2008 .

[23]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[24]  R. Trigo,et al.  Rainfall data analysis using wavelet transform. , 2003 .