The Development of a Hybrid Wavelet-ARIMA-LSTM Model for Precipitation Amounts and Drought Analysis

Abstract

Investigation of quantitative predictions of precipitation amounts and forecasts of drought events are conducive to facilitating early drought warnings. However, there has been limited research into or modern statistical analyses of precipitation and drought over Northeast China, one of the most important grain production regions. Therefore, a case study at three meteorological sites which represent three different climate types was explored, and we used time series analysis of monthly precipitation and the grey theory methods for annual precipitation during 1967–2017. Wavelet transformation (WT), autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) methods were utilized to depict the time series, and a new hybrid model wavelet-ARIMA-LSTM (W-AL) of monthly precipitation time series was developed. In addition, GM (1, 1) and DGM (1, 1) of the China Z-Index (CZI) based on annual precipitation were introduced to forecast drought events, because grey system theory specializes in a small sample and results in poor information. The results revealed that (1) W-AL exhibited higher prediction accuracy in monthly precipitation forecasting than ARIMA and LSTM; (2) CZI values calculated through annual precipitation suggested that more slight drought events occurred in Changchun while moderate drought occurred more frequently in Linjiang and Qian Gorlos; (3) GM (1, 1) performed better than DGM (1, 1) in drought event forecasting.