Research on precipitation prediction based on a complete ensemble empirical mode decomposition with adaptive noise–long short-term memory coupled model

Abstract

Scientific precipitation predicting is of great value and guidance to regional water resources development and utilisation, agricultural production and drought and flood control. Precipitation is a non-linear, non-smooth time series with significant stochasticity and uncertainty. In this paper, a Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) with Long Short-Term Memory (LSTM) model is developed for predicting annual precipitation in Zhengzhou City. Which is compared with a single Long Short-Term Memory model, an EEMD (Ensemble Empirical Mode Decomposition)-LSTM model, a CEEMD (Complementary Ensemble Empirical Mode Decomposition)-LSTM model, CEEMDAN-ARIMA (Auto Regressive Integrated Moving Average) and CEEMDAN-RNN (Recurrent Neural Network). The results show that the mean absolute error (MAPE), root mean square error (RMSE) and coefficient of determination (R2) of the coupled CEEMDAN-LSTM model are 2.69%, 17.37 mm and 0.9863, respectively. The prediction accuracy is significantly higher than that of the other five models, indicating that the proposed model has high prediction accuracy and can be used for annual precipitation forecasting in Zhengzhou City.

A Novel Hybrid Model of CEEMDAN-CNN-SAGU for Shanghai Copper Price Prediction

“…CEEMDAN's effectiveness in mitigating modal confusion and reducing residual noise align with our utilization of CEEMDAN in our research. CEEMDAN solves the problem of modal confusion in EEMD decomposition and improves the problem of residual noise to a certain extent [19]. Kala et al used the CEEMDAN-LSTM model to predict monthly rainfall across India.…”