Recent Advancements in the Prediction of Air Quality Monitoring Using AI Techniques : A Comprehensive Review

Economic activities have degraded the quality of air, which is an important natural resource. Much effort has undergone to predict when air quality would be low, but the majority of these studies lack the longitudinal data needed to accurately adjust for seasonal and other confounding variables. This survey covers the subject of air quality monitoring in depth, looking at present methods to find different metrics and their effects on environmental health. To evaluate air quality in various places, the study used a variety of approaches that includes both fixed and mobile monitoring approaches. The factors contributing to deterioration of the air quality have been determined as particulate matter (PM2.5 and PM10), Sulfur Dioxide (SO2), Nitrogen Dioxide (NO2), Carbon Monoxide (CO), Ozone (O3), and Volatile Organic Compounds (VOCs).Several methods have been studied which are mainly focused on predicting and forecasting the air quality. The study revealed the importance of machine and deep learning based automated approaches to predict the air quality. Similarly, the technological advancements have facilitated promising solutions for AQI measurement by using IoT and cloud-based systems. The main goal of this paper is to examine current approaches and to determine the difficulties encountered by current approaches in AQI monitoring.