FastCTM (v1.0): Atmospheric chemical transport modelling with a principle-informed neural network for air quality simulations

Abstract. Chemical transport models (CTM) have wide and profound applications in air quality simulations and managements. However, its applications are often constrained by high computational burdens. In this study, we developed a neural network based CTM model (FastCTM) to efficiently simulate ten air pollutant composition variables, including major PM_2.5 species of SO₄^2-, NO₃^-, NH₄⁺, organic matters and other inorganic components, coarse part of PM₁₀, SO₂, NO₂, CO and O₃. The FastCTM has a principle-informed structure by explicitly encoding atmospheric physical and chemical processes in a basic simulator. Specifically, in the simulator, five neural network modules are proposed to respectively represent five major atmospheric processes of primary emissions, transport, diffusion, chemical reactions and depositions. Given 1-hour initial condition data, the FastCTM is able to simulate future 24-hour concentrations of the ten air pollutants with corresponding meteorology fields and emissions as input. The FastCTM is trained with operational forecast data from a numerical CTM model named Community Multiscale Air Quality (CMAQ) in 2018–2022. The well-trained FastCTM is evaluated comparing to the long-term CMAQ forecast in an independent year 2023, and achieves high agreements with mean RMSE values of 9.1, 11.9, 4.4, 4.0, 48.9 and 10.9 μg/m³ and R² values of 0.8, 0.81, 0.8, 0.83, 0.9 and 0.7 for PM_2.5, PM₁₀, SO₂, NO₂, CO, and O₃. Besides, assessed against hourly site observations of six criteria pollutants, the RMSE values of FastCTM have small relative differences of 4.3 %, 4.2 %, -2.8 %, -1.7 %, -0.3 % and -3.2 % compared to that of CMAQ. The FastCTM model also exhibited reasonable responses of air quality to meteorological variables of air temperature, wind speed and planetary boundary layer height, as well as to input pollutant emissions. Furthermore, due to the principles-oriented structure, internal process analysis could be performed by FastCTM to quantify the specific contribution from each of the five processes for hourly air pollutant concentration changes. In a nutshell, FastCTM has multi-functional advantages in air pollutant concentration simulations, sensitivity analysis and internal process analysis with high computation efficiencies on GPU and accuracy.