The Use of a Recurrent Neural Network for Forecasting Ozone Concentrations in the City of Agadir (Morocco)

Abstract

Air quality is a complex issue which depends mutually on source emission, land topography, meteorological parameters and used mathematical tools for forecasting its dispersion. One of major toxic gas is ozone which could be dangerous to human health. The present work has been developed to forecast ozone concentrations in the city of Agadir using a Recurrent Neural Network (RNN). Predicting ozone concentrations will provide useful information, especially, for decision makers in order to prevent and reduce the ozone human health impacts. The data was collected in the most polluted area in the city using a mobile monitoring station during a period of 60 days. We have tested different neural network architectures and we found that the 1-hour forecast model, whose input parameters are a combination of meteorological parameters as well as CO and SO 2 , give the most optimal results. Coefficient of Correlation (CC), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were used to evaluate the statistical agreement between observed and predicted values. The model successfully predicts the ozone concentration by a bias of 4 µg.m −3 over 24 hours and which a correlation coefficient is more than 80%. This work highlights the ability of the recurrent neural networks to forecast air pollutant concentrations in urban areas.

Assessment of health impact of the surface ozone on a population residing at Agadir city (Morocco) using the AirQ+ model

“…With regards to Agadir City, several sources of air pollution could be listed like dust from industrial and port units, trash incineration, traffic emissions, among others. So far, some physico-chemical studies on air pollutants and ozone concentrations were carried out in Agadir City [13,14]. The aim of the present study was then to assess and evaluate the health impact of ozone concentrations on a population living at Agadir city.…”