Prediction of Daily PM2.5 Concentrations Using Neural Networks at 3 Urban Monitoring Stations With Diverse Land Uses

Abstract

This study aimed to develop an effective forecasting model for daily average PM2.5 concentration using a multilayer perceptron (MLP) neural network. The model was applied to 3 air quality monitoring stations in Mashhad, Iran—Sajjad, Torogh, and Vila—representing different urban land use types. A separate network was trained for each station. The optimal network architecture was determined by tuning the number of neurons in the hidden layer, using input variables such as the previous day’s meteorological parameters (wind speed, temperature, precipitation, solar radiation, and relative humidity), PM2.5 concentration, and temporal indicators (day of the week and month). Data standardization and early stopping were used to enhance generalization. The model performed best at Sajjad station, with an R2 of .79 and MAE of 5.54 µg/m3. Performance at Torogh was acceptable, while Vila showed weaker results. The model detected PM2.5 exceedance events with a true positive rate of 66% to 74% and a false alarm rate as low as 0.18 at Sajjad. Differences in topography, pollution sources, and microclimate conditions influenced spatial variability in accuracy. These findings suggest that MLP neural networks are effective tools for daily air pollution prediction and can support localized early warning systems.