ABSTRACT
This study aimed to model and forecast the average daily concentration of inhalable particulate matter (PM10), in the Greater Vitoria Region (GVR), Espírito Santo, Brazil, using the SARIMAX model, for the period from January 1st, 2012 to April 30th, 2015. Data set from the State Environmental Institute was used. The Enseada do Suá station was chosen for purposes of prediction and forecasting. Some meteorological parameters (wind speed, relative humidity, rainfall and temperature) measured at the GVR were taken as explanatory variables of PM10 concentrations. Based on modelling performance indicators, it was verified the SARIMAX model (1.0.2) (0.1.1)7 is the most accurate between the ones studied, purposing to predict and forecast the air quality in the GVR. The statistical performance of the SARIMAX model was better than the ARMA model, with regard to prediction of regular air quality events. Among the evaluated meteorological variables, wind speed and rainfall were significant and improved the model estimated. Regarding to air quality forecasting, the time series models showed satisfactory results.
Keywords:
air pollution; PM10; time series; SARIMAX