Long-Term Prediction of Hydrometeorological Time Series Using a PSO-Based Combined Model Composed of EEMD and LSTM

The accurate long-term forecasting of hydrometeorological time series is crucial for ensuring the sustainability of water resources, environmental conservation, and other related fields. However, hydrometeorological time series usually have strong nonlinearity, non-stationarity, and complexity. Therefore, it is extremely challenging to make long-term forecasts of hydrometeorological series. Deep learning has been widely applied in time series prediction across various fields and exhibits exceptional performance. Among the many deep learning techniques, Long Short-Term Memory (LSTM) neural networks possess robust long-term predictive capabilities for time series analysis. Signal decomposition technology is utilized to break down the time series into multiple low complexity and highly stationary sub-sequences, which are then individually trained using LSTM before being reconstructed to generate accurate predictions. This approach has significantly advanced the field of time series prediction. Therefore, we propose an EEMD-LSTM-PSO model, which employs Ensemble Empirical Mode Decomposition (EEMD), to decompose the hydrometeorological time series and subsequently construct an LSTM model for each component. Furthermore, the Particle Swarm Optimization (PSO) algorithm is utilized to optimize the coefficients and reconstruct the final prediction outcomes. The performance of the EEMD-LSTM-PSO model is evaluated by comparing it with four other models using four evaluation indicators: root mean square error (RMSE), mean absolute percentage error (MAPE), correlation coefficient (R), and Nash coefficient (NSE) on three real hydrometeorological time series. The experimental results show that the proposed model exhibits exceptional performance compared with the other four models, and effectively predicts long-term hydrometeorological time series.