Study on the 3DVar emission inversion method combined with machine learning in CMAQ

The air quality model is increasingly important in air pollution forecasting and controlling. Emissions significantly impact the accuracy of air quality models. This research studied the 3DVar (three-dimensional variational) emission inversion method based on machine learning in CMAQ (The Community Multiscale Air Quality modeling system). The ExRT(extremely randomized trees method) machine learning conversion matrixes were established to convert the pollutant concentration innovations to the corresponding emission intensity innovations, extended 3DVar to emission inversion. The O3 and NO2 concentration, NOx and VOCs emissions are modeled using machine learning, taking account of the nonlinearity of the O3-NOx-VOCs processes. This method significantly improved the simulation ability of O3. Taking the air pollution process in the BTH region from January 15 to 30, 2019 as an example, ExRT-3DVar (3DEx) and Nudging (Nud) emission assimilation experiments were caried out. Compared with the simulation without assimilation (NODA), the Nudging method has better assimilation effects on PM10 and NO2, with the regional errors reduced by 14%, 2%, and the temporal errors reduced by 31%, 34%; ExRT-3DVar has better effects on the assimilation of PM2.5, O3, SO2, the regional errors were reduced by 40%, 29%, 13%, and the temporal errors were reduced by 49%, 10%, 33%. This simplicity, efficiently and extensibility framework of ExRT-3DVar method has been proved to be a good way to adjust emissions in CMAQ and still remains much to be done in the future.