Mimicking atmospheric photochemical modelling with a deep neural network.

Fast and accurate prediction of ambient ozone (O) formed from atmospheric photochemical processes is crucial for designing effective O pollution control strategies in the context of climate change. The chemical transport model (CTM) is the fundamental tool for O prediction and policy design, however, existing CTM-based approaches are computationally expensive, and resource burdens limit their usage and effectiveness in air quality management. Here we proposed a novel method (noted as DeepCTM) that using deep learning to mimic CTM simulations to improve the computational efficiency of photochemical modeling. The well-trained DeepCTM successfully reproduces CTM-simulated O concentration using input features of precursor emissions, meteorological factors, and initial conditions. The advantage of the DeepCTM is its high efficiency in identifying the dominant contributors to O formation and quantifying the O response to variations in emissions and meteorology. The emission-meteorology-concentration linkages implied by the DeepCTM are consistent with known mechanisms of atmospheric chemistry, indicating that the DeepCTM is also scientifically reasonable. The DeepCTM application in China suggests that O concentrations are strongly influenced by the initialized O concentration, as well as emission and meteorological factors during daytime when O is formed photochemically. The variation of meteorological factors such as short-wave radiation can also significantly modulate the O chemistry. The DeepCTM developed in this study exhibits great potential for efficiently representing the complex atmospheric system and can provide policymakers with urgently needed information for designing effective control strategies to mitigate O pollution.