Prediction of Indoor Air Exposure from Outdoor Air Quality Using an Artificial Neural Network Model for Inner City Commercial Buildings

NO2 and particulate matter are the air pollutants of most concern in Ireland, with possible links to the higher respiratory and cardiovascular mortality and morbidity rates found in the country compared to the rest of Europe. Currently, air quality limits in Europe only cover outdoor environments yet the quality of indoor air is an essential determinant of a person’s well-being, especially since the average person spends more than 90% of their time indoors. The modelling conducted in this research aims to provide a framework for epidemiological studies by the use of publically available 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 building, 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 parallel indoor and outdoor diurnal monitoring had been carried out on site. This modelling methodology has been shown to provide reasonable predictions of average NO2 indoor air quality compared to the monitored data, but did not perform well in the prediction of indoor PM2.5 concentrations. Hence, this approach could be used to determine NO2 exposures more rigorously of those who work and/or live in the city centre, which can then be linked to potential health impacts.

[1]  Zarita Zainuddin,et al.  Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data , 2011, Appl. Soft Comput..

[2]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[3]  I. K. Larissi,et al.  Application of Multiple Linear Regression Models and Artificial Neural Networks on the Surface Ozone Forecast in the Greater Athens Area, Greece , 2012 .

[4]  Matti Jantunen,et al.  Exposure chain of urban air PM2.5-associations between ambient fixed site, residential outdoor, indoor, workplace and personal exposures in four European cities in the EXPOLIS-study , 2002 .

[5]  Trevor Hancock,et al.  Indicators of Environmental Health in the Urban Setting , 2002, Canadian journal of public health = Revue canadienne de sante publique.

[6]  Manfred Neuberger,et al.  Reducing ambient levels of fine particulates could substantially improve health: a mortality impact assessment for 26 European cities , 2008, Journal of Epidemiology & Community Health.

[7]  Zhong-Ren Peng,et al.  Fine-scale estimation of carbon monoxide and fine particulate matter concentrations in proximity to a road intersection by using wavelet neural network with genetic algorithm , 2015 .

[8]  Tracy L. Thatcher,et al.  Effects of room furnishings and air speed on particle deposition rates indoors , 2002 .

[9]  S L Zeger,et al.  Exposure measurement error in time-series studies of air pollution: concepts and consequences. , 2000, Environmental health perspectives.

[10]  G. Solomon,et al.  Health effects of diesel exhaust , 2003 .

[11]  Ruwim Berkowicz,et al.  OSPM - A Parameterised Street Pollution Model , 2000 .

[12]  Brian Broderick,et al.  A GIS model for personal exposure to PM10 for Dublin commuters , 2015 .

[13]  J. Navarro-Pedreño.  Numerical Methods for Least Squares Problems , 1996 .

[14]  Judith H. Heerwagen,et al.  Green buildings, organizational success and occupant productivity , 2000 .

[15]  Rashmi S. Patil,et al.  A GENERAL FINITE LINE SOURCE MODEL FOR VEHICULAR POLLUTION PREDICTION , 1989 .

[16]  C. Dimitroulopoulou,et al.  Modelling of indoor exposure to nitrogen dioxide in the UK , 2001 .

[17]  Wei-Zhen Lu,et al.  Ground-level ozone prediction by support vector machine approach with a cost-sensitive classification scheme. , 2008, The Science of the total environment.

[18]  N. Bofinger,et al.  Impact of microenvironmental nitrogen dioxide concentrations on personal exposures in Australia. , 2000, Journal of the Air & Waste Management Association.

[19]  Mohd Talib Latif,et al.  Spatial Assessment of Air Quality Patterns in Malaysia Using Multivariate Analysis , 2012 .

[20]  S. Hoff,et al.  Prediction of Indoor Climate and Long-term Air Quality Using a Building Thermal Transient model, Artificial Neural Networks and Typical Meteorological Year , 2009 .

[21]  E. Thacker.  Lung inflammatory responses. , 2006, Veterinary research.

[22]  Jefrey I Kindangen.  Artificial neural networks and naturally ventilated buildings : A method of predicting window size and location with subsequent effect on interior air motion using neural networks , 1996 .

[23]  K. Katsouyanni,et al.  Short-term effects of air pollution on hospital emergency outpatient visits and admissions in the greater Athens, Greece area. , 1995, Environmental research.

[24]  Laurence Gill,et al.  Indoor/outdoor air pollution relationships in ten commercial buildings: PM2.5 and NO2 , 2014 .

[25]  Constantinos Sioutas,et al.  Potential Role of Ultrafine Particles in Associations between Airborne Particle Mass and Cardiovascular Health , 2005, Environmental health perspectives.

[26]  W. Rom,et al.  Particulate matter inhibits DNA repair and enhances mutagenesis. , 2008, Mutation research.

[27]  M. Madden,et al.  Toxicity and metal content of organic solvent extracts from airborne particulate matter in Puerto Rico. , 2006, Environmental research.

[28]  Matti Jantunen,et al.  Personal exposures to NO2 in the EXPOLIS-study: relation to residential indoor, outdoor and workplace concentrations in Basel, Helsinki and Prague , 2001 .

[29]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[30]  I. Momas,et al.  Personal exposure of Paris office workers to nitrogen dioxide and fine particles , 2002, Occupational and Environmental Medicine.

[31]  Yu Xue,et al.  Prediction of particulate matter at street level using artificial neural networks coupling with chaotic particle swarm optimization algorithm , 2014 .

[32]  Martin Hvidberg,et al.  Evaluation of AirGIS: a GIS-based air pollution and human exposure modelling system , 2008 .

[33]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[34]  Dong Wang,et al.  Learning machines: Rationale and application in ground-level ozone prediction , 2014, Appl. Soft Comput..

[35]  D. Dockery,et al.  Effect of air-pollution control on death rates in Dublin, Ireland: an intervention study , 2002, The Lancet.

[36]  Giorgio Corani,et al.  Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning , 2005 .

[37]  Great Britain. Foreign Office..  Census of population , 1988 .

[38]  D. Dockery,et al.  An association between air pollution and mortality in six U.S. cities. , 1993, The New England journal of medicine.