Research on Hydrological Time Series Prediction Based on Combined Model

Abstract

Water level prediction of river runoff is an important part of hydrological forecasting. The change of water level not only has the trend and seasonal characteristics, but also contains the noise factors. And the water level prediction ability of a single model is limited. Since the traditional ARIMA (Autoregressive Integrated Moving Average) model is not accurate enough to predict nonlinear time series, and the WNN (Wavelet Neural Network) model requires a large training set, we proposed a new combined neural network prediction model which combines the WNN model with the ARIMA model on the basis of wavelet decomposition. The combined model fit the wavelet transform sequences whose frequency are high with the WNN, and the scale transform sequence which has low frequency is fitted by the ARIMA model, and then the prediction results of the above are reconstructed by wavelet transform. The daily average water level data of the Liuhe hydrological station in the Chu River Basin of Nanjing are used to forecast the average water level of one day ahead. The combined model is compared with other single models with MATLAB, and the experimental results show that the accuracy of the combined model is improved by 7% compared with the traditional wavelet network under the appropriate wavelet decomposition function and the combined model parameters.