A Data Assimilation Method Combined with Machine Learning and Its Application to Anthropogenic Emission Adjustment in CMAQ

Anthropogenic emissions play an important role in air quality forecasting. To improve the forecasting accuracy, use of nudging as data assimilation method, combined with extremely randomized trees (ExRT) machine learning was developed and applied to adjust anthropogenic Community Multiscale Air Quality modeling system (CMAQ). This nudging–ExRT method can iterate forecast is suitable for linear nonlinear emissions. For example, episode between 15 30 January 2019 simulated China’s Beijing–Tianjin–Hebei (BTH) region. PM2.5, correlation coefficient site averaged concentration (Ra) increased from 0.85 0.94, root mean square error (RMSEa) decreased 24.41 9.97 µg/m3. O3, Ra 0.75 0.81, RMSEa 13.91 12.07 These results showed that significantly skills be routine future.