International Forestry & Environment Symposium, Trabzon, Turkey, 7 - 10 November 2017, pp.73
Abstract
In this work, ozone (O3), nitrogen
oxides (NOx), and carbon monoxide (CO) concentrations and some
meteorological parameters measured hourly from May 2016 to August 2017, have
been analyzed in order to examine the interaction patterns between O3 and
NOx, CO, air temperature, wind speed, relative humidity, and air
pressure by taking into account the diurnal variations of them at the urban site
(Akçaabat ) in Trabzon. Variations of O3 levels have been modeled
via the TLBO method considering the effects of certain parameters (NOx and
CO concentration, air temperature, wind speed, relative humidity, and air
pressure) called the independent variables. The accuracy of the TLBO method has
been determined and these methods have been applied to four different functions:
quadratic, exponential, linear, and power. Some statistical indices (mean square
error, root mean square error, mean absolute error, mean absolute percentage
error, and determination coefficient) have been used to evaluate the
performance of these models. The TLBO method with quadratic forms has obtained
better predictions. As a result, it is shown TLBO can be used for optimization of
the regression function coefficients in modeling some air pollutants
interaction.
Keywords: Air pollution, ozone concentration, TLBO
algorithm, modeling.