Prediction of indoor air exposure from outdoor air quality using an artificial neural network model for inner city commercial buildings

Abstract

NO 2 and particulate matter are the air pollutants of most concern in Ireland , with possible links to the high er respiratory and cardiovascular mortality and morbidity rates found in the country compared to the rest of Europe. Currentl y, air quality limits in Europe only cover outdoor environments yet the quality of indoor air is a n essential determinant of a person ’ s well - being, especially since the average person spends more than 90% of their time indoors. T he modelling con ducted in this research aims to provid e a framework for epidemiological studies by the use of publically availab le data from fixed outdoor monitoring stations to predict indoor air quality more accurately. Predictions are made using two modelling techniques, the Personal - exposure Activity Location Model (PALM) , to predict outdoor air quality at a particular b uilding, and Artificial Neural Networks, to model the indoor/outdoor relationship of the building. This joint approach has been used to predict indoor air concentrations for three inner city commercial buildings in Dublin , where diurnal monitoring of indoo r and outdoor had been carried out on site. T his modelling methodology has been shown to provide reasonable predictions of average NO 2 indoor air quality compared to the monitored data , but did not perform well in the prediction of indoor PM 2. 5 concentrati ons. Hence, this approach could be used to determine NO 2 exposures more rigorously of those who work and/or live in the city centre , which can then be linked to potential health impacts .