Examining the Applicability of Wavelet Packet Decomposition on Different Forecasting Models in Annual Rainfall Prediction

Accurate precipitation prediction can help plan for different water resources management demands and provide an extension of lead-time the tactical strategic planning courses action. This paper examines applicability several forecasting models based on wavelet packet decomposition (WPD) in annual rainfall forecasting, a novel hybrid framework (WPD-ELM) is proposed coupling extreme learning machine (ELM) WPD. The works this be described as follows: (a) WPD used to decompose original data into sub-layers; (b) ELM model, autoregressive integrated moving average model (ARIMA), back-propagation neural network (BPNN) are employed realize computation decomposed series; (c) results attain final prediction. Four evaluation indexes (RMSE, MAE, R, NSEC) adopted assess performance models. indicate that WPD-ELM outperforms other significantly enhance In conclusion, promising alternative effective pre-processing technique producing convincing