Application of Machine Learning to Air Pollution Studies: A Systematic Review
Marvelous Ukachukwu *
Department of Geological Sciences, Nnamdi Azikiwe University, Awka, Nigeria.
Nnemeka Uzoamaka
Department of Geological Sciences, Nnamdi Azikiwe University, Awka, Nigeria.
Nnama Elochukwu
Department of Geological Sciences, Nnamdi Azikiwe University, Awka, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
Air pollution is a serious global issue that threatens human life and health, as well as the environment. Machine learning algorithms can be used to predict air pollution level data from both natural and anthropogenic activities. Environmental and government agencies can use these speculations to issue air pollution alerts. This review work is an attempt at the recent status and development of scientific studies on the use of machine learning algorithms to model air pollution challenges. This study uses the scientific web as a primary search engine and covers over 100 highly peer-reviewed articles from 2000-2022. Therefore, this review paper aims to highlight the various application methods of machine learning, notably data mining, in air pollution control and monitoring. It also comprehensively analyses published works by renowned scholars and authors worldwide, discussing how machine learning has been used in mitigating air pollution. By examining the chronological trends of machine learning in air pollution, this review paper provides an up-to-date account of the successes achieved in regulating air pollution using machine learning techniques. Additionally, it identifies areas that require further research, critically analyzing the current state of knowledge and potential research directions.
Keywords: Machine learning, environmental pollution, air pollution, algorithm, anthropogenic