Abstract: In the new century,along with the rapid development of Chinese economy,air pollution in many areas of China is relatively serious,while the government is paying more and more attention to air pollution,and its efforts to control air pollution are increasing.Currently,six pollutants that have the greatest impact on China’s air quality are O₃,SO₂,NO₂,CO,PM₁₀,PM_2.5.Therefore,predicting and forecasting the concentrations of the six pollutants and making corresponding control adjustments in time have become the urgent needs to protect the health of residents and build a beautiful China.At present,the mainstream solution for pollutant prediction is WRF-CMAQ prediction system,which is based on two parts,physical and chemical reaction of pollutants and meteorological simulation.However,due to the current research on the generation mechanism of pollutants such as ozone is still on the way,the prediction of WRF-CMAQ model has large errors.Therefore,this paper adopts a deep neural network for secondary modeling of pollutant concentrations to reduce the prediction error.At the same time,this paper adopts the federal learning method,and uses federal learning for data training for multiple monitoring stations to improve the model generalization ability.Experiment results show that the deep neural network scheme reduces the mean square error value to at most 3.93% compared to the primary prediction results of one WRF-CMAQ.Moreover,the scheme with federal learning improves the perfor-mance by up to 68.89% compared to a single monitoring site in extensive tests.

Key words: Federated learning, Deep neural networks, Pollutant concentration prediction, WRF-CMAQ