An Attention-Based Hybrid Model Combining Graph Convolutional Networks and Gated Recurrent Units for Ground-Level Ozone Spatiotemporal Prediction

Ozone pollution has emerged as a pressing issue in urban environments, with its adverse effects on human health and ecosystems increasingly being scrutinized. This study proposes a novel model to achieve accurate prediction of near-surface ozone concentrations. The model integrates the strengths of Graph Convolutional Networks (GCN) and Gated Recurrent Units (GRU) to capture spatial dependencies among monitoring stations and temporal dynamics of ozone concentrations, respectively. Additionally, an attention-based feature fusion module is developed to dynamically balance the contributions of spatial and temporal features, further enhancing prediction performance. Furthermore, a multi-stage training strategy is introduced to adapt the model better to autoregressive time series prediction tasks. Using data from 30 air quality monitoring stations in Beijing as test subjects, the model demonstrates excellent predictive performance, even for longer-term predictions (+6 hours). Compared to commonly used methods, the proposed model significantly reduces the average prediction error, exhibiting greater stability and robustness, especially in multi-step prediction tasks where it effectively mitigates error accumulation. This study provides a reliable and robust spatiotemporal air quality modeling framework for predicting near-surface ozone concentrations, offering a significant reference for improving air quality management and understanding the dynamics of ozone pollution.