Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting

Xukai Zhang (Beijing Institute of Technology) · Shuliang Wang (Beijing Institute of Technology) · Guangyin Jin (National University of Defense Technology) · Ziqiang Yuan (Beijing Institute of Technology) · Hanning Yuan (Beijing Institute of Technology) · Sijie Ruan (Beijing Institute of Technology)

advection-diffusion-reaction equationair pollutionchemical transportclimate governancedata-driven models deep learning modelecological sustainabilityenvironmental challengeseulerian representationphysics-informed neural networkpollutant distributionsrmse improvementspatiotemporal dynamicsspatiotemporal evolutionstate-of-the-art baselines

Air pollution remains one of the most critical environmental challenges globally, posing severe threats to public health, ecological sustainability, and climate governance. While existing physics-based and data-driven models have made progress in air quality forecasting, they often struggle to jointly capture the complex spatiotemporal dynamics and ensure spatial continuity of pollutant distributions. In this study, we introduce CTENet, a novel chemical transport deep learning model that embeds the Advection-Diffusion-Reaction equation into a Physics-Informed Neural Network (PINN) framework using an Eulerian representation to model the spatiotemporal evolution of pollutants. Extensive experiments on two real-world datasets demonstrate that CTENet consistently outperforms state-of-the-art (SOTA) baselines, achieving a remarkable RMSE improvement of 45.8% on the USA dataset and 21.0% on the China dataset.