Affiliation:
1. Ministry of Education, Nanjing Normal University
2. COMSATS University Islamabad
3. Mir Chakar Khan Rind University of Technology
4. Hainan University
5. Nanjing Normal University
6. Ministry of Education, Jiangxi Normal University
7. Bahauddin Zakariya University
Abstract
Abstract
Due to rapid expansion in the global economy and industrialization, PM2.5 (particles smaller than 2.5 µm in aerodynamic diameter) pollution has become a key environmental issue. The public health and social development directly affected by high PM2.5 levels. In this paper, ambient PM2.5 concentrations along with meteorological data are forecasted using time series models, including random forest (RF), prophet forecasting model (PFM) and autoregressive integrated moving average (ARIMA) in Anhui province, China. The results indicate that the RF model outperformed the PFM and ARIMA in the prediction of PM2.5 concentrations, with cross-validation coefficients of determination R2, RMSE and MAE values of 0.80, 11.50 µg/m3 and 8.13 µg/m3, respectively. PFM achieved the average results (R2 = 0.73, RMSE = 13.21 µg/m3 and MAE = 9.17 µg/m3), while the predicted results by ARIMA are comparatively poorer (R2 = 0.63, RMSE = 15.56 µg/m3 and MAE = 10.64 µg/m3) than RF and PFM. These findings reveal that the RF model is the most effective method for predicting PM2.5 and can be applied to other regions for new findings.
Publisher
Research Square Platform LLC