We present the results of a neural network model designed for the forecasting of hourly PM2.5 concentrations in Santiago, Chile. The study focuses on the observed values at two of the monitoring stations which are located in the south-west zone of the city and which are among the stations that register the highest concentrations during the period between April and August. This is the season when air quality is very often in ranges that are harmful for the population and some restrictions to emissions become convenient.
The forecasting model is a multilayer neural network. The input variables are observed values of hourly PM10 and PM2.5 concentrations measured at the station of interest and in a neighboring station at 7 PM of the present day, and some observed and forecasted meteorological variables. NO2 concentrations during morning and afternoon hours are also used as input, which may be associated with secondary particle formation. Implemented models are trained with 2014 and 2015 data and tested with 2016 values. Information is collected until 7 PM of the present day and the largest forecasting error up to 21 hours in advance is 32%.
Accuracy of forecasting is better than that obtained with a neural model used previously for the forecasting of hourly PM2.5 concentrations in the north-west zone in Santiago. Our neural models show better results than those obtained with linear models with the same input variables. The developed models provide a tool for anticipating episodes in Santiago and other cities with similar unfavorable conditions for pollutant dispersion.