Precipitation forecast based on CEEMD–LSTM coupled model

Abstract

Abstract Precipitation forecasting is an important guide to the prevention and control of regional droughts and floods, the rational use of water resources and the ecological protection. The precipitation process is extremely complex and is influenced by the intersection of many variables, with significant randomness, uncertainty and non-linearity. Based on the advantages that complementary ensemble empirical modal decomposition (CEEMD) can effectively overcome modal aliasing, white noise interference, and the ability of long short-term memory (LSTM) networks to handle problems such as gradient disappearance. A CEEMD–LSTM coupled long-term and short-term memory network model was developed and adopted for monthly precipitation prediction of Zhengzhou City. The performance shows that the CEEMD–LSTM model has a mean absolute error of 0.056, a root mean square error of 0.153, a mean relative error of 2.73% and a Nash efficiency coefficient of 0.95, which is better than the CEEMD–Back Propagation (BP) neural network model, the LSTM model and the BP model in terms of prediction accuracies. This demonstrates its powerful nonlinear and complex process learning capability in hydrological factor simulation for regional precipitation prediction.