On the predictability of short-lived particulate matter around a cement plant in Kerman, Iran: machine learning analysis

One of the greatest environmental risks in the cement industry is particulate matter emission (i.e., PM(2.5) and PM(10)). This paper aims to develop descriptive-analytical solutions for increasing the accuracy of predicting particulate matter emissions using resample data of Kerman cement plant. Photometer instruments DUST TRAK and BS-EN-12341 method were used to determine concentration of PM(2.5) and PM(10). Sampling was performed on 4 environmental stations of Kerman cement plant in the four seasons. In order to accurate assessment of particulate matter concentration, a new model was proposed to resample cement plant time series data using Pandas in Python. The effect of meteorological parameters including wind speed, relative humidity, air temperature and rainfall on the particulate matter concentration was investigated through statistical analysis. The results indicated that the maximum annual average of 24-h of PM(2.5) belonged to the east side (opposite the clinker depot) in 2019 (31.50 μg m(−3)) and west side (in front of the mine) in 2020 (31.00 μg m(−3)). Also, maximum annual average of 24-h of PM(10) belonged to the west side (in front of the mine) in 2020 (121.00 μg m(−3)) and east side (opposite the clinker depot) in 2020 (120.75 μg m(−3)). The PM(2.5) and PM(10) concentrations are more than the allowable limit. The results demonstrate that particulate matter concentration increases with increasing relative humidity and rainfall. Finally, the SARIMA model was used to predict the particulate matter concentration. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s13762-022-04645-3.