Research on Monthly Precipitation Prediction Model Based on WOA-CEEMDAN-BiLSTM
Yong Fang, Menchita F. Dumlao, Joey S. Aviles · 2024
In order to further improve the accuracy and generalization ability of precipitation model prediction based on the nonlinear and non-stationary characteristics of precipitation data, this paper proposes a precipitation prediction model based on Whale Optimization Algorithm (WOA), Complete Ensemble Empirical Mode Decomposition (CEEMDAN), and Bidirectional Long Short Term Memory Network (BiLSTM). Compared to the default parameters of CEEMDAN, WOA is used to optimize the key parameters of CEEMDAN, decomposing precipitation data into several intrinsic mode functions (IMFs) to extract multi-scale feature information. Predict each IMF using the BiLSTM model and reconstruct the predicted results into the final precipitation forecast. This article takes the historical precipitation data of a city in Guangdong Province as an example to verify that the model has high accuracy and robustness in precipitation prediction.