Air Quality Prediction with A Meteorology-Guided Modality-Decoupled Spatio-Temporal Network

Air quality prediction plays a crucial role in public health and environmental protection. Accurate air quality prediction is a complex spatiotemporal problem, which involves pollutant spatiotemporal dependencies and meteorological influences that govern pollutant dispersion and transformation. However, existing predictive models often underestimate the critical influence of atmospheric conditions by treating air quality and meteorological data as a single, homogeneous modality or by using only limited surface-level features, which impairs performance. To overcome this, we propose modality-decoupled spatio-temporal network (MDSTNet),, an encoder–decoder framework that takes historical air quality observations and multipressure-level meteorological data as input, explicitly modeling them as distinct modalities, while uniquely leveraging multistep weather forecasts as dynamic prompts to guide prediction. Meantime, we construct ChinaAirNet, the first nationwide dataset combining air quality records with multipressure-level meteorological observations. Experimental results on ChinaAirNet and a public dataset KDDCUP-Beijing demonstrate MDSTNet’s superiority, substantially reducing 48-hour prediction errors by 17.54% compared to the state-of-the-art model, showcasing the significant advantage of our meteorology-guided, modality-decoupled design.