Air Pollution Modelling with Deep Learning: A Review

  • Yasin Akın Ayturan
  • Zeynep Cansu Ayturan
  • Hüseyin Oktay Altun
Keywords: Deep learning, air pollution estimation, artificial neural networks, generative adversarial model.


Air pollution is one of the fundamental environmental problems of the industrialized world due to its adverse effects on all organisms. Several institutions warn that there exist serious air pollution in many regions of the world. When all devastating effects of air pollutants considered, it is crucial to create valid models to predict air pollution levels in order to determine future concentrations or to locate pollutant sources. These models may provide policy implications for governments and central authorities in order to prevent the excessive pollution levels. Though there are a number of attempts to model pollution levels in the literature, recent advances in deep learning techniques are promising more accurate prediction results along with integration of more data.  In this study, a detailed research about modelling with deep learning architectures on real air pollution data is given. With the help of this research we attempt to develop air pollution architectures with deep learning in future and enhance the results further with insights from recent advances of deep learning research such as Generative Adversarial Networks (GANs), where two competing networks are working against each other, one for creating a more realistic data and the other one to predict the state.  

How to Cite
Yasin Akın Ayturan, Zeynep Cansu Ayturan, & Hüseyin Oktay Altun. (2019). Air Pollution Modelling with Deep Learning: A Review. International Journal of Environmental Pollution and Environmental Modelling, 1(3), 58-62. Retrieved from