A hybrid optimization prediction model for PM2.5 based on VMD and deep learning

Abstract

PM2.5 has caused serious harm to human health and the environment, so it is particularly important to accurately predict PM2.5 concentration. Aiming at the problem that the nonlinear features of PM2.5 data are difficult to be learned accurately, which results in low prediction accuracy, the WOA-VMD-BiLSTM hybrid model is proposed in this paper. This model optimizes the parameters of the variational modal decomposition (VMD) by the Whale Optimization Algorithm (WOA), after which the PM2.5 sequence is broken down into several intrinsic modal function (IMF) using the VMD. Next, the nonlinear and temporal features of each IMF are captured using a bidirectional long short-term memory neural network (BiLSTM). Finally, all features are fused to get the prediction of PM2.5 concentration. According to the experimental findings, in contrast to the most accurate baseline model, the proposed model reduced the values of RMSE by 18.12, 20.17, and 5.36 in 1∼6 h, 7–12 h, and 13–24 h, respectively. In addition, the model can successfully capture the trend of PM2.5 concentration changes in the long-term prediction.