Air Pollution Surveillance Systems: A Review of the modelling and the Forecasting Technologies

Abstract

Air pollution is a major concern, particularly in modern cities due to its significant effects on public health and the global economy. The importance of the air quality  information makes the need for extremely precise real-time monitoring systems essential. The researchers are compelled to create future air pollution surveillance systems by utilising cutting-edge technologies like machine learning techniques, big data technologies, sensors, and the Internet of Things for suggesting a stable and effective model for the stated purpose due to the conventional air monitoring systems' limited data access, high cost, and inability to be scaled up.  The ability of machine learning algorithms to forecast air pollution by means of general pattern and abrupt changes is demonstrated by extensive real-time air pollution trials. For gathering and analysing air data, smart devices are required. By analysing and gathering recent research in this area, this review paper focuses on providing an overview of air pollution surveillance systems (APSS) and emphasises data sources, monitoring, and forecasting models to enhance the various components of air polluting models. Additionally, it provides light on a variety of research-related problems and difficulties.