Modeling PM2.5 forecast using a self-weighted ensemble GRU network: Method optimization and evaluation

Abstract

Due to the rapid industrial development and global concern about air pollution, understanding the dynamics of PM2.5 concentration has become a key aspect of air quality prediction. Many deep learning and mode decomposition techniques have been explored to capture the temporal and nonlinear features of PM2.5 concentration data. However, most of the existing methods ignore the differences in prediction losses of individual subsequences, resulting in lower prediction accuracy. To address this limitation, we proposed an ensemble gated recurrent unit (GRU) model that incorporated a self-weighted total loss function based on variational mode decomposition (VMD). In this approach, the PM2.5 concentration series were decomposed using the VMD, and then each decomposed subsequence (including the residual sequence) was fed into the GRU and the predicted loss of the subsequence was then calculated. For the model to output optimal predictions, we used a self-weighted ensemble loss function to adaptively optimize the prediction loss for each subsequence. Specifically, larger weights were assigned to the model's subsequences with higher predictive losses to better focus on those with higher predictive losses. In addition, the hyperparameter of the model was adjusted to adapt to various datasets in different domains. Experimental results on the three datasets show that our model performs better than the VMD-GRU and single GRU models. This validates the effectiveness of our model. Our approach has the advantage of plug-and-play, making it easier to seamlessly integrate deep learning techniques and pattern decomposition methods into air quality prediction.