چکیده:
The impact of air pollution and environmental issues on public health is one of the main topics studied in many cities around the world. Ozone is a greenhouse gas that contributes to global climate. This study was conducted to predict and model ozone of Yazd in the lower atmosphere by an adaptive neuro-fuzzy inference system (ANFIS). All the data were extracted from 721 samples collected daily over two successive years, from April 2012 to 29 March 2014. The concentration of pollutants and meteorological variables including NOX, temperature, wind speed and wind direction were considered as input and ozone (O3) as the output of model. The results showed that among five membership functions used in the model, the Gaussian membership function with R2 equal to 0.949, RMSE equal to 2.430 and correlation coefficient equal to 0.974 was obtained as the best model to predict the concentration of ozone in the lower atmosphere. This study showed that predicting and modelling ozone using an adaptive neuro-fuzzy inference system (ANFIS) is appropriate and, due to the expansion of the city of Yazd in the not too distant future, it
is necessary to pay more attention to the permissible threshold values of pollutants such as ozone.
خلاصه ماشینی:
"ir Desert 19-2 (2014) 131-135 Modelling the formation of Ozone in the air by using Adaptive Neuro-Fuzzy Inference System (ANFIS) (Case study: city of Yazd, Iran) L.
This study was conducted to predict and model ozone of Yazd in the lower atmosphere by an adaptive neuro-fuzzy inference system (ANFIS).
This study showed that predicting and modelling ozone using an adaptive neuro-fuzzy inference system (ANFIS) is appropriate and, due to the expansion of the city of Yazd in the not too distant future, it is necessary to pay more attention to the permissible threshold values of pollutants such as ozone .
There have been various studies in predicting and modelling ozone concentrations by means of multiple linear regression (MLR), artificial neural networks (ANNs) and multi-gene genetic programming (MGP) (Sousa et al.
For simulation of network inference systems (fuzzy- adaptive) a data set is required consisting four variables: NOx, temperature, wind speed and wind direction as network input and the ozone concentration as output of the network.
A study was conducted in 2013 on modelling and predicting the formation of ozone in the air of Mashhad city using a neural fuzzy network based on inference fuzzy-adaptive systems.
A study by Johanyak and Kovacs, on the prediction of surface ozone concentration based on a fuzzy model, showed the model applied using LESFRI to have the best results with a low number of values (Johanyak and Kovacs, 2011).
Modeling and predicting the formation of ozone air Mashhad city using a neural network-based fuzzy inference system and fuzzy-adaptive."