Determining Effective Factors Regarding Weather and Some Types of Air Pollutants in Seasonal Changes of PM۱۰ Concentration Using Tree-Based Algorithms in Yazd City

Introduction: This study was carried out with the aim of determining weather parameters and air pollutants affecting seasonal changes of particulate matter of less than ۱۰ microns (PM۱۰) in Yazd city using Random Forest (RF) and extreme gradient boosting (Xgboost) models. Materials and Methods: The required data was obtained from ۲۰۱۸ to ۲۰۲۲. Levene’s test was applied to investigate the significant difference in the variance of PM۱۰ values in ۴ different seasons, and Boruta algorithm was used to select the best predictive variables. RF and Xgboost models were trained using two-thirds of the input data and were tested using the remaining data set. Their performance was evaluated based on R۲, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Nash–Sutcliffe Model Efficiency Coefficient (NSE). Results: The RF showed a higher performance in predicting PM۱۰ in all the study seasons (R۲  > ۰.۸۵; RMSE < ۲۲). The contribution of dust concentration and relative humidity in spring PM۱۰ changes was more than other variables. For summer, wind direction and ozone were identified as the most important variables affecting PM۱۰ concentration. In the autumn and winter, air pollutants and dust concentration had the greatest effect on PM۱۰, respectively. Conclusion: RF model could explain more than ۸۵% of PM۱۰ seasonal variability in Yazd city. It is recommended to use the model to predict the changes of this air pollutant in other regions with similar climatic and environmental conditions. The results can also be useful for providing suitable solutions to reduce PM۱۰ pollution hazards in Yazd city.

Keywords:

Air Pollution , Particulate Matter , Dust , Machine Learning , Random Forest.