Paper Title
Spatiotemporal Air Pollutant Concentration Prediction Model

Abstract
Air quality holds significant importance due to its direct influence on both public health and the environment, especially in major developing countries. Due to large-scale industrialization and technological advances, there has been increased pressure on air quality. Air quality is of vital significance as it directly influences general wellbeing and the climate, with poor air quality leading to respiratory illnesses and contributing to climate change. Studying and improving air quality is critical for safeguarding human well-being and maintaining a sustainable planet. In this paper, we present an array of techniques designed for the prediction of air pollution levels, focusing on pollutants like PM2.5 and NO2. We discussed several machine learning, deep learning methodologies and statistical techniques and a few hybrid models combining machine and deep learning models. Furthermore, we critically analyse the limitations associated with these methods, along with suggestions for potential enhancements to advance the field of research. Keywords - Air pollution, Spatiotemporal, Machine Learning, Deep Learning, Particulate Matter (PM2.5), Prediction Model