Wavelet neural network model for reservoir inflow prediction

In this study, a wavelet neural network (wnn) model is proposed for monthly reservoir inflowprediction by combining the discrete wavelet transform (dwt) and levenberg-marquardt optimizationalgorithm-based feed forward neural networks (ffnn). the study area covers the basin of kemer damwhich is located in the aegean region of turkey. monthly meteorological data were decomposed intowavelet sub-time series by dwt. ineffective sub-time series have been eliminated by using all possibleregression method and evaluating the mallows' cp coefficients to prevent collinearity. then, effectivesub-time series components have been used as the new inputs of neural networks. dwt has been alsointegrated with multiple linear regressions (wreg) within the study. the results of wavelet neuralnetwork (wnn) model and wreg have been compared with conventional feed forward neural networks(ffnn) and multiple linear regression (reg) models. when the statistical-based criteria are examined, ithas been observed that the dwt method has increased the performances of feed forward neural networksand regression methods. the results determined in the study indicate that the wnn is a successful tool tomodel the monthly inflow series of dam and can give good prediction performances than other methods.