Amirkabir University of Technology AUT Journal of Civil Engineering 2588-2899 4 4 2020 12 01 Prediction of the Air Quality by Artificial Neural Network Using Instability Indices in the City of Tehran-Iran 517 528 3592 10.22060/ajce.2019.17018.5609 EN Razieh Farhadi Graduated Student, Environmental Sciences Department, Hakim Sabzevari University, Sabzevar, Iran Mojtaba Hadavifar Assistant Professor, Environmental Sciences Department, Hakim Sabzevari University, Sabzevar, Iran Mazaher Moeinaddini Assistant Professor, Environmental Sciences Department, University of Tehran, Tehran, Iran Mahmood Amintoosi Assistant Professor, Faculty of Mathematics and Computer Science, Hakim Sabzevari University, Sabzevar, Iran Journal Article 2019 09 07 <strong>Today, air pollution is a serious environmental problem becoming a global concern for human beings Air quality is influenced by emissions, meteorological parameters, and topography. The effect of these parameters can be predicted using statistical methods. In the current study, the data in the period of March 2012 to October 2013 are used. These data have been gathered from the stations of the Department of Environment and Air Quality Control Organization (Azadi and Sharif stations) in Tehran city. The main purpose was to predict the air quality of the next day and emissions of carbon monoxide and suspended particles under the influence of instability indices and meteorological parameters using the Artificial Neural Network. Results of the modeling process showed that the concentration of pollutants is strongly influenced by meteorological parameters. Also, prediction of the PM₁₀ concentration of the next day using meteorological parameters (RMSE=29.03, <em>R</em>=0.76), instability indices and meteorological parameters (RMSE=28.13, <em>R</em>=0.76) were better than those obtained for AQI predicted by meteorological parameters (RMSE=20.81, <em>R</em>=0.50) and instability indices and meteorological parameters (RMSE=19.23, <em>R</em>=0.47). In general, the predicted values of PM₁₀ and CO were better compared to AQI. It can be concluded that an artificial neural network couldn’t load the model properly for AQI compared to PM₁₀.</strong> https://ajce.aut.ac.ir/article_3592_fef16f151e26cab7d9e3fb3304f3cf2b.pdf