Spatial estimation of urban air pollution with the use of artificial neural network models. (October 2018)

• Record Type: Journal Article
• Authors: Alimissis, A.; Philippopoulos, K.; Tzanis, C.G.; Deligiorgi, D.
• Is Part Of: Atmospheric environment. Volume 191(2018)
• Page Start: 205
• Page End: 213
• Publication Date: 2018-10
• Subjects: Air quality -- Spatial interpolation -- Artificial neural networks; Air -- Pollution -- Periodicals; Air -- Pollution -- Meteorological aspects -- Periodicals; 551.51
• DOI: 10.1016/j.atmosenv.2018.07.058
• Languages: English
• ISSNs: 1352-2310

Abstract

Abstract: The deterioration of urban air quality is considered worldwide one of the primary environmental issues and scientific evidence associates the exposure to ambient air pollution with serious health effects. This fact highlights the importance of generating accurate fields of air pollution for quantifying present and future health related risks. Interpolation methods for point estimations in the field of air pollution modelling enable the estimation of pollutant concentrations in unmonitored locations. The main objective of this study is to evaluate two interpolation methodologies, Artificial Neural Networks and Multiple Linear Regression, using data from a real urban air quality monitoring network located at the greater area of metropolitan Athens in Greece. The results for five regulated air pollutants (Nitrogen dioxide, Nitrogen monoxide, Ozone, Carbon monoxide and Sulphur dioxide) are compared through the use of a set of correlation and difference statistical measures and residuals distribution. Artificial neural networks are found in most cases to be significantly superior, especially where the air quality network density is limited, leading to a decreased degree of spatial correlations among the monitoring sites. Highlights: ANN models are superior compared to MLR for air pollution spatial forecasting. The air quality monitoring network density affects the ANN predicting ability. ANN models incorporate the most significant spatial variability features. The critical high-end O3 concentrations are well represented by the ANNs. ANNs could be used operationally for modelling air pollution spatial variability.