Air Quality Prediction Using Machine Learning and Deep Learning: An Exploratory Study

Over the past few decades, urbanization and industrialization have expanded rapidly in both emerging and developed countries. There is growing concern between the government and the public regarding the adverse effects of air pollution on human health, which has led to an increased emphasis on sustainable development as a solution to this problem. Modern industries release waste products into the atmosphere in the form of liquid droplets, solid particles, and gas molecules, leading to a high concentration of particulate matter. In turn, this can lead to harmful impacts on human health. On the other hand, forecasting techniques aid in predicting the future levels of pollution in particular locations and may even recommend helpful preventative measures. Air pollution forecasting has been topic of research in numerous studies, the majority of which are based on sequence models (generate predictions after being trained with raw pollution data). This study examined the machine learning and deep learning techniques used to predict air pollution and air quality. This information would help researchers provide in-depth knowledge about the latest techniques and future challenges related to the prediction of air pollution.