Measurements of aerosol parameters in the surface air layer with sets of Panasonic PM2.5 optical sensors and throughout the atmospheric column by the photometric method at urban and background observation sites in the Middle Urals for 2016-2019 are analyzed. The features of the intraannual and diurnal variations in aerosol parameters in the surface air layer and in the atmospheric column are compared. Correlations between the PM2.5 concentration, AOD, and meteorological parameters in the two regions are also studied. Multivariate regression models for estimating the logarithm of PM2.5 concentration ensure much higher quality than single-factor models. The significant predictors are determined: boundary layer height (blh, m), ln AOD, normalized relative vegetation index (NDVI), relative air humidity (Hu, %), and air pressure ( P , Pa).