Hourly Air Quality Index (AQI) Forecasting Using Machine Learning Methods

Abstract

Air Quality Index (AQI) is an index to inform the daily air quality. AQI is a dimensionless quantity to show the state of air pollution simplifying the information of concentrations in. Air quality indexes have been established for each of the five pollutants located in an interesting area to study in as Algeciras (Spain). Hourly data of air pollutants, available during 2010–2015, were analysed for the development of the proposed AQI. This work proposes a two-step forecasting approach to obtain future values, eight hours ahead, of AQI using Machine Learning methods. ANN, SVR and LSTM are capable of modelling non-linear time series and can be trained to accurately generalize when a new database is presented.