Prediction of NOx Emissions with A Novel ANN Model in Adana

Abstract

NOx exmissions are one of the typical air pollutants that has drawn worldwide attention. NO emissions from air cause detrimental effects on the environment and human health such as lung cancer, asthma, allergic rhinitis, and mental diseases. Therefore, real-time NOx monitoring has been very popular research topics in atmospheric and environmental science. However, the spatial coverage of monitoring stations within Adana is limited and thus often insufficient for exposure. Moreover, NOx monitoring stations are also lacking to reveal the influences of meteorological and air pollutant effects. In this study, artificial neural network (ANN), which is a biological mimicked computer algorithm that simulates the functions of neurons using artificial neurons, has been used to present a quantitative determination of the NOx emission in Adana through the influences of temperature (°C), wind rate (km/h), and SO2 (µg/m³) on NOx emissions. The high R2 values in testing dataset lead to the conclusion that the artificial neural network model provides predictions. The developed model in study is a useful tool for the design and planning of air pollution control policies as well as reducing economic cost. The developed model in study is a useful tool for the design and planning of air pollution control policies as well as reducing economic cost.

Keywords

• Adana
• Air Pollution
• NOx Emissions
• Artificial Neural Network
• Prediction

References

1. 1. Wang, J. and G. Song, A deep spatial-temporal ensemble model for air quality prediction. Neurocomputing, 314 (2018) 198-206.
2. 2. Wen, C., et al., A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. Science of The Total Environment, 654 (2019) 1091-1099.
3. 3. Wang, X.-C., et al., Air pollution terrain nexus: A review considering energy generation and consumption. Renewable and Sustainable Energy Reviews, 105 (2019) 71-85.
4. 4. Azid, A., et al., Prediction of the level of air pollution using principal component analysis and artificial neural network techniques: A case study in Malaysia. Water, Air, & Soil Pollution, 225(8) (2014) 2063.
5. 5. Lal Benjamin, N., et al., Air quality prediction using artificial neural network. IJCS, 2(4) (2014) 07-09.
6. 6. Baawain, M.S. and A.S. Al-Serihi, Systematic approach for the prediction of ground-level air pollution (around an industrial port) using an artificial neural network. Aerosol and air quality research, 14(1) (2014) 124-134.
7. 7. Shakil, M., et al., Soft sensor for NOx and O2 using dynamic neural networks. Computers & Electrical Engineering, 35(4) (2009) 578-586.
8. 8. Park, J.-H., et al., Historic and futuristic review of electron beam technology for the treatment of SO2 and NOx in flue gas. Chemical Engineering Journal, 2018.

9. 9. Hoffman, S., Short-time forecasting of atmospheric NOx concentration by neural networks. Environmental Engineering Science, 23(4) (2006) 603-609.
10. 10. Shi, J.P. and R.M. Harrison, Regression modelling of hourly NOx and NO2 concentrations in urban air in London. Atmospheric Environment, 31(24) (1997) 4081-4094.
11. 11. Carbajal-Hernandez, J.J., et al., Assessment and prediction of air quality using fuzzy logic and autoregressive models. Atmospheric Environment, 60 (2012) 37-50.
12. 12. Sofuoglu, S.C., et al., Forecasting ambient air SO2 concentrations using artificial neural networks. Energy Sources, Part B, 1(2) (2006) 127-136.
13. 13. Unsal, F., Globalization and the mid-rank city:: The case of Adana, Turkey. Cities 21(5) (2004) 439-449.
14. 14. https://www.havaizleme.gov.tr/, 2019
15. 15. https://www.worldweatheronline.com/adana-weather-averages/adana/tr.aspx, 2019