A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hybrid neural network models for hydrologic time series forecasting
Applied Soft Computing
Hi-index | 0.00 |
Based on the advantages of both wavelet analysis and artificial neural network, the wavelet neural network (WNN) model is established through coupling wavelet transform with BP neural network for forecasting the basin sediment yield. The time sequence of the annual sediment yield is decomposed and reconstructed into the low-frequency and high-frequency components by wavelet transform; then these components are predicted by optimized BP neural network respectively. Finally, the sum of the predicting values is the forecasting result of the sediment yield. The result shows that the hybrid model, compared with the traditional BP (TB) model, has high accuracy in the simulation and test of basin sediment yield, which can provide a scientific basis for ecological environment protection and water resource management in a basin.