No abstract

No abstract

One of the key elements in achieving sustainable water resources and environmental management is forecasting the future condition of the surface water resources. In this study, the performance of a river flow forecasting model is improved when different input combinations and signal processing techniques are applied on multi-layer backpropagation neural networks. Haar, Coiflet and Daubechies wavelet analysis are coupled with backpropagation neural networks model to develop hybrid wavelet neural networks models. Different models with different input selections and structures are developed for daily, weekly and monthly river flow forecasting in Ellen Brook River, Western Australia. Comparison of the performance of the hybrid approach with that of the original neural networks indicates that the hybrid models produce significantly better results. The improvement is more substantial for peak values and longer-term forecasting, in which the Nash-Sutcliffe coefficient of efficiency for monthly river flow forecasting is improved from 0.63 to 0.89 in this study. Figure 3. Nash-Sutcliffe coefficients for (a) training and (b) validation sets, for different backpropagation neural network and wavelet neural network (WNN) models. ANN, artificial neural network. This figure is available in colour online at wileyonlinelibrary.com/journal/rra FLOW FORECASTS WITH SIGNAL PROCESS TECHNIQUE 249 Figure 5. Scatter plots of observed and forecasted river flow with the best-fitted backpropagation neural network (BPNN) and wavelet neural network (WNN) models for one step ahead daily, weekly and monthly forecasting. This figure is available in colour online at wileyonlinelibrary.com

No abstract

In this paper, an advanced stream flow forecasting model is developed by applying data-preprocessing techniques on adaptive neuro-fuzzy inference system (ANFIS). Wavelet multi-resolution analysis is coupled with an ANFIS model to develop a hybrid wavelet neuro-fuzzy (WNF) model. Different models with different input selection and structures are developed for daily, weekly and monthly stream flow forecasting in Railway Parade station on Ellen Brook River, Western Australia. The stream flow time series is decomposed into multi-frequency time series by discrete wavelet transform using the Haar, Coiflet and Daubechies mother wavelets. The wavelet coefficients are then imposed as input data to the neuro-fuzzy model. Models are developed based on Takagi-Sugeno-Kang fuzzy inference system with the grid partitioning approach for initializing the fuzzy rule-based structure. Mean-square error and Nash-Sutcliffe coefficient are chosen as the performance criteria. The results of the application show that the right selection of the inputs with high autocorrelation function improves the accuracy of forecasting. Comparing the performance of the hybrid WNF models with those of the original ANFIS models indicates that the hybrid WNF models produce significantly better results especially in longer-term forecasting.