Forecasting Urban Air Quality with Machine and Deep Learning
Authors
Department of CSE (AIML) New Institute of Technology, Kolhapur, Maharashtra, India (India)
Department of CSE (AIML) New Institute of Technology, Kolhapur, Maharashtra, India (India)
Department of CSE (AIML) New Institute of Technology, Kolhapur, Maharashtra, India (India)
Article Information
DOI: 10.51583/IJLTEMAS.2026.151000083
Subject Category: Learning
Volume/Issue: 15/10 | Page No: 1035-1045
Publication Timeline
Submitted: 2026-10-29
Accepted: 2026-11-03
Published: 2026-11-10
Abstract
Fine particulate matter and other urban pollutants are now forecast routinely with data-driven models, yet the evidence is scattered across cities, pollutants, horizons and error metrics. This paper is a selective, qualitative synthesis, not a systematic review: it reads two published surveys and a purposive sample of nine experimental studies (2018–2025) covering Beijing, Seoul, Tehran, Taiyuan, Chicago, Taiwan, Indian cities, an Italian dataset and a large Chinese monitoring network. The sample is skewed toward East and South Asia and Iran and contains no Transformer-based, satellite-input or hybrid physics–machine-learning study, so it does not represent the whole field. Within this sample three observations recur. In the two studies with detailed horizon-wise results, recurrent networks held their accuracy better than shallow models several hours ahead, while at one hour tree ensembles came close to the best neural results. Input design (neighbouring stations, weather forecasts, calendar features, cleaned signals) appears in several studies to matter at least as much as the algorithm, although this is an impression from illustrative ablations, not a systematic test. Finally, reported scores are seldom comparable between papers, so headline rankings deserve caution. All numbers are taken from the original papers; no experiment was re-run.
Keywords
Air Quality Forecasting; PM2.5; Machine Learning; LSTM; Ensemble Learning; Spatiotemporal Modelling
This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Downloads
References
1. M. Méndez, M. G. Merayo, and M. Núñez, “Machine learning algorithms to forecast air quality: A survey,” Artif. Intell. Rev., vol. 56, no. 9, pp. 10031–10066, 2023. [Google Scholar] [Crossref]
2. D. Iskandaryan, F. Ramos, and S. Trilles, “Air quality prediction in smart cities using machine learning technologies based on sensor data: A review,” Appl. Sci., vol. 10, no. 7, Art. no. 2401, 2020. [Google Scholar] [Crossref]
3. H. Liu, Q. Li, D. Yu, and Y. Gu, “Air quality index and air pollutant concentration prediction based on machine learning algorithms,” Appl. Sci., vol. 9, no. 19, Art. no. 4069, 2019. [Google Scholar] [Crossref]
4. M. R. Delavar et al., “A novel method for improving air pollution prediction based on machine learning approaches: A case study applied to the capital city of Tehran,” ISPRS Int. J. Geo-Inf., vol. 8, no. 2, Art. no. 99, 2019. [Google Scholar] [Crossref]
5. Y.-C. Liang, Y. Maimury, A. H.-L. Chen, and J. R. C. Juarez, “Machine learning-based prediction of air quality,” Appl. Sci., vol. 10, no. 24, Art. no. 9151, 2020. [Google Scholar] [Crossref]
6. S. K. Singh, R. Jain, D. Palaniappan, K. Parmar, T. Premavathi, and J. Gothania, “Spatiotemporal analysis and machine learning-based prediction of air quality in Indian urban cities,” Environ. Res. Technol., vol. 8, no. 4, pp. 809–822, 2025. [Google Scholar] [Crossref]
7. D. Zhu, C. Cai, T. Yang, and X. Zhou, “A machine learning approach for air quality prediction: Model regularization and optimization,” Big Data Cogn. Comput., vol. 2, no. 1, Art. no. 5, 2018. [Google Scholar] [Crossref]
8. T. Xayasouk, H. Lee, and G. Lee, “Air pollution prediction using long short-term memory (LSTM) and deep autoencoder (DAE) models,” Sustainability, vol. 12, no. 6, Art. no. 2570, 2020. [Google Scholar] [Crossref]
9. H. Karimian et al., “Evaluation of different machine learning approaches to forecasting PM2.5 mass concentrations,” Aerosol Air Qual. Res., vol. 19, pp. 1400–1410, 2019. [Google Scholar] [Crossref]
10. S. Li, G. Xie, J. Ren, L. Guo, Y. Yang, and X. Xu, “Urban PM2.5 concentration prediction via attention-based CNN–LSTM,” Appl. Sci., vol. 10, no. 6, Art. no. 1953, 2020. [Google Scholar] [Crossref]
11. X. Yi, J. Zhang, Z. Wang, T. Li, and Y. Zheng, “Deep distributed fusion network for air quality prediction,” in Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, London, U.K., 2018, pp. 965–973. [Google Scholar] [Crossref]
12. D. W. Byun and K. L. Schere, “Review of the governing equations, computational algorithms, and other components of the Models-3 Community Multiscale Air Quality (CMAQ) modeling system,” Appl. Mech. Rev., vol. 59, no. 2, pp. 51–77, 2006. [Google Scholar] [Crossref]
13. G. A. Grell, S. E. Peckham, R. Schmitz, S. A. McKeen, G. Frost, W. C. Skamarock, and B. Eder, “Fully coupled “online” chemistry within the WRF model,” Atmos. Environ., vol. 39, no. 37, pp. 6957–6975, 2005. [Google Scholar] [Crossref]
This work is licensed under CC BY 4.0