Analysis of deep learning approaches for air pollution prediction

Due to the urban and industrial growth, many evolving countries suffer from excessive air pollution. The growing concern about air pollution has been raised by the government and people because it affects individual's health and sustainable development globally. Recent methods for the prediction of air quality primarily use vast models; furthermore, these approaches yield inconsistent results, inspiring us to inspect air quality prediction methods based on deep learning architectures. While there is a range of efforts in the literature to figure pollution levels, recent developments in deep learning techniques, along with the incorporation of more data, offer more precise predictive accuracy. The paper analyses the previous deep learning frameworks proposed for air quality prediction. This paper discusses and reviews the different deep learning architectures with their advantages and disadvantages for air pollution forecasting.