Environ Sci Pollut Res Int. 2025 Jul 2. doi: 10.1007/s11356-025-36657-0. Online ahead of print.
ABSTRACT
In this study, different statistical methodologies were combined to assess the relationship between PM10 concentrations and meteorological variables (temperature, relative humidity, wind direction and speed, and atmospheric pressure) and their associations with other pollutants (CO, NO2, NO, and O3) recorded during the period 2021-2024 at Mendoza City, Argentina. The results indicate that increased humidity and temperature might reduce PM10 levels by enhancing particle dispersion and deposition. Positive correlations between PM10, NO, and NO2 suggest a shared origin, likely from vehicle emissions. To further analyze PM10 behavior, prediction models were developed to categorize PM10 levels as “good” (≤ 45 μg/m3) or “bad” (>45 μg/m3) based on a air quality guidelines from WHO. The performance of the random forest (RF) and logistic regression (LR) algorithms were evaluated and compared. Additionally, the influence of atmospheric variables and pollutant concentrations was also assessed to determine their impact on PM10 predictions. RF model demonstrated the highest predictive performance for PM10 level. Results indicate that NOx (NO2 and NO) significantly contribute to PM10 formation, likely due to shared anthropogenic sources. Temperature, humidity, and wind speed also impact PM10 predictions, though to a lesser extent than pollutant concentrations. The inclusion of these variables highlights the role in the dispersion and transformation of air pollutants. Implementing such models could provide policymakers with real-time data to enhance pollution control and public health protection.
PMID:40601188 | DOI:10.1007/s11356-025-36657-0
