Ambient PM2.5 Prediction Based on Prophet Forecasting Model in Anhui Province, China

Due to recent development in different sectors such as industrialization, transportation, and the global economy, air pollution is one of the major issues in the twenty-first century. In this work, we aimed to predict ambient PM2.5 concentration using the prophet forecasting model (PFM) in Anhui Province, China. The data were collected from 68 air quality monitoring stations to forecast both short-term and long-term PM2.5 concentrations. The determination coefficient (R2), root mean squared error (RMSE), and mean absolute error (MAE) were used to determine the accuracy of the model. According to the obtained results, the predicted R, RMSE, and MAE values by PFM for PM2.5 were 0.63, 15.52 μg/m3, and 10.62 μg/m3, respectively. The results indicate that the actual and predicted values were significantly fitted and PFM accurately predict PM2.5 concentration. These findings are supportive and helpful for local bodies and policymakers to deal and mitigate air pollution problems in the future.