Prediction of mortality resulted from NO2 concentration in Tehran by Air Q+ software and artificial neural network
- 85 Downloads
In this study, for the first time, the combination of Air Q+ software and wavelet neural network was used to predict the mortality rate caused by the increase in NO2 concentration in Tehran. In the combination of these two softwares, the wavelet neural network software was used to predict daily NO2 concentration based on 12 effective parameters, and then the annual concentration of NO2 was calculated using the daily concentration of wavelet neural network output. Then, annual concentration of NO2 was used as the input of Air Q+ software. The mortality rate was calculated by Air Q+ software. In this research, the most appropriate predictive algorithm for neural network was studied and layer recurrent algorithm was the most appropriate algorithm. Then, capability of this network was enhanced to predict future NO2 concentration by wavelet transformation, and wavelet neural network was designed. Also, NO2 concentration is predicted for future 47 months by using of the time series of the previous data and the wavelet neural network. Analyzing the sensitivity of mortality resulted from NO2 concentration was done by using of wavelet neural network and Air Q+ software, and it was concluded that the increase or decrease in the parameters affecting NO2 concentration will affect the mortality rate. This research has identified petrol consumption as the most influential parameter. The conclusion is that by lowering the 10% of petrol consumption, the mortality based on NO2 concentration in ambient air will decrease about 50%.
KeywordsPrediction Air pollution Artificial neural network Air Q+ NO2
The authors would like to thank Tehran Weather Bureau and Tehran Municipality.
- Babanezhad E, Amini Rad H, Hosseini Karimi SS, Qaderi F (2017) Investigating nitrogen removal using simultaneous nitrification-denitrification in transferring wastewater through collection networks with small-diameter pipes. Water Pract Technol 12:396–405. https://doi.org/10.2166/wpt.2017.044 CrossRefGoogle Scholar
- Garson GD (1991) Interpreting neural-network connection weights. ArtifIntell 6:46–51Google Scholar
- Golbaz S, Farzadkia M, Kermani M (2010) Determination of Tehran air quality with emphasis on air quality index (AQI); 2008–2009. Iran Occup Health 6:62–68Google Scholar
- Kamarehie B, Ghaderpoori M, Jafari A et al (2017) Quantification of health effects related to SO2 and NO2 pollutants using Air quality model. J Adv Environ Health Res 5:44–50Google Scholar
- Ozcan HK, Ucan ON, Sahin U et al (2006) Artificial neural network modeling of methane emissions at Istanbul Kemerburgaz–Odayeri landfill site. J Sci Ind Res 65:128–134Google Scholar
- Qaderi F, Ayati B, Ganjidoust H (2011) Role of moving bed biofilm reactor and sequencing batch reactor in biological degradation of formaldehyde wastewater, Iran. J Environ Health Sci Eng 8:295–306Google Scholar
- Sidney Burrus C, Gopinath RA, Guo H (1998) Introduction to wavelets and wavelet transforms. Prentice-Hall, Inc., HoustonGoogle Scholar
- World Health Organization (2013) Health risks of air pollution in Europe: HRAPIE project. 60Google Scholar
- World Health Organization Europe (2001) Quantification of the Health Effects of Exposure to Air PollutionGoogle Scholar