Journal of Atmospheric and Environmental Optics ›› 2023, Vol. 18 ›› Issue (3): 227-234.

Previous Articles     Next Articles

Application of the Bayesian-based big data model in the analysis of the source of air pollution

WANG Lijun *, ZHOU Yu , WAN Lijuan , CHENG Liangliang   

  1. School of Electronic Information and Electrical Engineering, Hefei Normal University
  • Received:2022-02-08 Revised:2022-04-17 Online:2023-05-28 Published:2023-05-28

Abstract: A method for analyzing influencing factors of complex systems based on multi-dimensional Gaussian Bayesian classification algorithm is proposed, classification models for diverse range of PM2.5 are established, and then the analysis of the key influencing factors on complex systems is carried out in combination with Mahalanobis distance. Based on the weather and air quality data of Hefei City from 2013 to 2018, 8 main influencing factors for PM2.5, such as PM10, SO2, NO2, CO, O3 and so on, are screened out, and then the correlation between PM2.5 and the influencing factors is analyzed using scatter matrix. The PM2.5 analysis model based on Gaussian Bayesian classifier is established with these data. It is found that PM2.5 has a strong positive correlation with CO concentration, is selective to NO2, and has a negative correlation with O3. As for CO and SO2, a certain competitive mechanism between the two factors in the production of PM2.5 is observed.

Key words: big data technology, Gaussian Bayesian model, influencing factors, PM2.5, correlation analysis

CLC Number: