Poor air quality affects human health and exacerbates climate change, inducing temperature variations. Therefore, it is important to understand at local level the interactions between climate variability and air pollution to mitigate the effects of air pollution on human health. The aim of this paper is to explore the correlations between meteorological parameters, temperature (T), humidity (H) and air pressure (P) and particulate matter concentrations (PM1, PM2.5, PM10). Also, it is investigated the correlation between PM 2.5 and PM10, between noise, CO2, and PM concentrations. For this purpose, five hybrid Machine Learning models were employed to forecast the PMs concentrations and then the Air Quality Index (AQI). The data set was provided by an independent network of sensors for the period of September 22, 2021 – February 17, 2022. In the results we found, R² exceeds, in general, 0.96 and, in most cases, they can reach 0.99. The humidity was found to be the less significant variable on the PMs concentrations, and the best accuracy was found by combining the pressure with the temperature. In addition, PM10 concentrations were found effectively related to the PM2.5 concentrations and with a bit strongly to the PM1. The PM10 concentration is not strongly correlated to the Noise and CO2 data. Finally, several new relationships have been built to forecast the PMs concentrations and the AQI based on the best combinations of predictor variables found.