Application of artificial intelligence in air pollution monitoring and forecasting: A systematic review
Article
Chadalavada, Sreeni, Faust, Oliver, Salvi, Massimo, Seoni, Silvia, Raj, Nawin, Raghavendra, U., Gudigar, Anjan, Barua, Prabal Datta, Molinari, Filippo and Acharya, Rajendra. 2025. "Application of artificial intelligence in air pollution monitoring and forecasting: A systematic review." Environmental Modelling and Software. 185. https://doi.org/10.1016/j.envsoft.2024.106312
Article Title | Application of artificial intelligence in air pollution monitoring and forecasting: A systematic review |
---|---|
ERA Journal ID | 4673 |
Article Category | Article |
Authors | Chadalavada, Sreeni, Faust, Oliver, Salvi, Massimo, Seoni, Silvia, Raj, Nawin, Raghavendra, U., Gudigar, Anjan, Barua, Prabal Datta, Molinari, Filippo and Acharya, Rajendra |
Journal Title | Environmental Modelling and Software |
Journal Citation | 185 |
Article Number | 106312 |
Number of Pages | 15 |
Year | 2025 |
Publisher | Elsevier |
Place of Publication | United Kingdom |
ISSN | 1364-8152 |
1873-6726 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.envsoft.2024.106312 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S1364815224003736 |
Abstract | Air pollution poses a significant global health hazard. Effective monitoring and predicting air pollutant concentrations are crucial for managing associated health risks. Recent advancements in Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), offer the potential for more precise air pollution monitoring and forecasting models. This comprehensive review, conducted according to PRISMA guidelines, analyzed 65 high-quality Q1 journal articles to uncover current trends, challenges, and future AI applications in this field. The review revealed a significant increase in research papers utilizing ML and DL approaches from 2021 onwards. ML techniques currently dominate, with Random Forest being the most frequent method, achieving up to 98.2% accuracy. DL techniques show promise in capturing complex spatiotemporal relationships in air quality data. The study highlighted the importance of integrating diverse data sources to improve model accuracy. Future research should focus on addressing challenges in model interpretability and uncertainty quantification. |
Keywords | Air pollution; Artificial intelligence; Deep learning; Monitoring tools; Health; PRISMA guidelines |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 410402. Environmental assessment and monitoring |
Byline Affiliations | School of Engineering |
Anglia Ruskin University, United Kingdom | |
PolitoBIOMed Lab, Italy | |
School of Mathematics, Physics and Computing | |
Manipal Institute of Technology, India | |
School of Business | |
Centre for Health Research |
Permalink -
https://research.usq.edu.au/item/zx142/application-of-artificial-intelligence-in-air-pollution-monitoring-and-forecasting-a-systematic-review
Download files
1
total views0
total downloads1
views this month0
downloads this month