FORECASTING OF CRITERIA AIR POLLUTANTS’ CONCENTRATIONS WITH STATISTICAL MODELS
Published: 28 May 2015
Abstract: The adverse effects of air pollutants have become a common problem in many developed or developing countries because of the major risks to human and environmental health. Particulate matter, ground-level ozone, carbon monoxide, sulfur oxides, nitrogen oxides, and lead were defined as criteria air pollutants by Environmental Protection Agency (EPA) such as chronic respiratory problems, eye irritation, difficulty in breathing, and pulmonary and cardiovascular diseases, including cancers, it is significant to forecast the concentrations of pollutants. For this purpose, there are numerous statistical models such as artificial neural networks (ANN), multiple linear regressions (MLR) and Taguchi which are modeled the pollutant concentrations assessed. The Taguchi method developed by Genichi Taguchi is an effective design of experiments (DOE) approach and the impacts of several factors can be determined simultaneously with this method. ANN has also been used for predict the concentrations of pollutants depends on several input parameters such as wind direction, relative humidity, temperature, pressure. In the literature, ANN modeling studies generally compare with MLR because of the higher sensitivity of models. In this review, we investigated the statistical models that are used for forecasting air pollutant concentrations and compared the advantages, limitations and performance indicators of those models.
Keywords: statistical models, air pollution, design of experiments
Download full text
Back to the contents of the volume
© 2020 The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/3.0/
, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This permission does not cover any third party copyrighted material which may appear in the work requested.