Unit:
Κατεύθυνση Φυσική Περιβάλλοντος (ΕΦΑΡΜΟΣΜΕΝΗ ΦΥΣΙΚΗ)Library of the School of Science
Author:
Αλιμήσης Αναστάσιος
Supervisors info:
Δέσποινα Δεληγιώργη Αναπληρώτρια Καθηγήτρια
Original Title:
Χωρική εκτίμηση της ατμοσφαιρικής ρύπανσης σε αστική περιοχή με τη χρήση τεχνητών νευρωνικών δικτύων
Translated title:
Spatial estimation of urban outdoor air pollution with the use of artificial neural network models
Summary:
The deterioration of urban air quality is considered worldwide one of the
primary environmental issues and most recent 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 modeling 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 air pollutants (ozone, nitrogen dioxide,
nitrogen monoxide, sulfur dioxide and carbon monoxide) are compared through the
use of error measures in the estimation period (root mean squared error, mean
absolute error and mean absolute percentage error). Artificial neural networks
are found to be statistical significantly superior in most cases, especially
when a smaller number of stations is examined, and thus the non-linear
correlations are augmented.
Keywords:
Urban air pollution, interpolation, Artificial neural networks, Multiple linear regression, Spatial estimation
File:
File access is restricted.
document.pdf
5 MB
File access is restricted.
