Evaluation of different machine learning approaches and aerosol optical depth in PM2.5 prediction

Atmospheric Aerosol Optical Depth (AOD), derived from polar-orbiting satellites, has shown potential in PM2.5 predictions. However, this important source of data suffers from low temporal resolution. Recently, geostationary satellites provide AOD data in high temporal and spatial resolution. However, the feasibility of these data in PM2.5 prediction needs further study. In this paper, we analyzed the impact of AOD derived from Himawari-8 in PM2.5 predictions. Moreover, by combining wavelet, machine learning techniques, and minimum redundancy maximum relevance (mRMR), a novel hybrid model was proposed. The results showed that AOD missing rate over Yangtze River Delta region is the highest in Nanjing, Hefei, and Maanshan. In addition, missing rates are the lowest in winter and summer (∼80%). Moreover, we found that considering AOD, as an auxiliary variable in the model, could not improve the accuracy of PM2.5 predictions, and in some cases decreased it slightly. In comparison with other models, our proposed hybrid model showed higher prediction accuracy, R2 is improved by 11.64% on average, and root mean square error, mean absolute error, and mean absolute percentage error is reduced by 26.82%, 27.24%, and 29.88% respectively. This research provides a general overview of the availability of Himawari-8 AOD data and its feasibility in PM2.5 predictions. In addition, it evaluates different machine learning approaches in PM2.5 predictions. Our proposed framework can be used in other regions to predict different air pollutants concentrations and can be used as an aid for air pollution controlling programs.