Abstract We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two critical factors governing pollutant dynamics: topography and wind direction. Complex terrain can channel, block and trap pollutants, while wind acts as a primary driver of their transport and dispersion. Building on these insights, TopoFlow leverages a vision transformer architecture with two novel mechanisms: topography-aware attention, which explicitly models terrain-induced flow patterns and wind-guided patch reordering, which aligns spatial representations with prevailing wind directions. Trained on 6 years of high-resolution reanalysis data assimilating observations from over 1400 surface monitoring stations across China, TopoFlow achieves a PM 2.5 RMSE of 9.71 μg/m 3 , representing a 71–80% improvement over operational forecasting systems and a 13% improvement over state-of-the-art AI baselines. Forecast errors remain well below China’s 24-hour air quality threshold of 75 μg/m 3 (GB 3095-2012), enabling reliable discrimination between clean and polluted conditions. These performance gains are consistent across all four major pollutants and forecast lead times from 12 to 96 hours, demonstrating that principled integration of physical knowledge into neural networks can fundamentally advance air quality prediction.
Kheder et al. (2026) studied this question.