A Survey on Air Pollution Prediction Using Machine Learning Techniques

Abstract

Predicting air pollution levels is crucial because of the damage it may do to ecosystems and people\'s health. A comprehensive review of current methods and models for forecasting air pollution has been presented in this article. A thorough review of 32 scholarly publications explores various machine learning algorithms, statistical models, and hybrid approaches to predict future pollution concentrations accurately. We discuss the unique challenges of air quality prediction, including data variability, spatial-temporal correlations, and the effect of meteorological factors. The research divides existing prediction models into categories based on their methodologies, data requirements, and application scenarios, stressing their strengths and limitations. The study also looks at how new technologies like IoT sensors, deep learning, and ensemble techniques might improve the precision and dependability of air pollution predictions. Future research focuses on integrating real-time data, multi-source information fusion, and developing scalable, interpretable models for dynamic air quality management.

Introduction

1. Factors Contributing to Air Pollution

• Sources: Population density, industries, thermal power plants, energy and automotive sectors, and transportation modes.

• Pollutants: Key pollutants include PM2.5, PM10, CO?, CO, SO?, NO?, O?, and NH?.

• Consequences: Human health issues (e.g., lung cancer, respiratory infections, heart failure) and environmental effects (acid rain, climate change, smog, reduced visibility).

2. Importance of Air Quality Monitoring

• NGOs and global organizations like the WHO monitor Air Quality Index (AQI) using pollutants and meteorological data.

• WHO (2022) reported PM2.5 was responsible for 1.7 million deaths in India alone (2010–2019 data).

• Visakhapatnam, Andhra Pradesh, is highlighted as a heavily polluted industrial hub.

3. Predictive Modelling for AQI

• Traditional Models: Statistical and physical models are limited by the non-linear, complex nature of air pollution.

• Modern Methods: Machine learning (ML) and deep learning (DL), including RNNs and LSTMs, are better suited due to their ability to model temporal dependencies using historical data.

4. Literature Survey on Prediction Methods

• Studies cover a range of ML/DL methods like regression, ensemble models, and specifically RNNs/LSTMs for air quality prediction.

• Key Findings:

  • Chang et al. (2020): LSTM works well for time-series air pollution forecasting.

  • Lavanya et al. (2024): IoT combined with ML enables real-time predictions.

  • Other studies show varying levels of focus on RNNs, ensemble models, and AI-based spatiotemporal analysis.

5. Feature Extraction in Air Pollution Prediction

• Feature extraction improves model accuracy by refining input data.

• Common sources: meteorological data, sensor outputs, spatial transfer.

• Notable studies:

  • Ma et al. (2020): Used Bi-LSTM with spatial data.

  • Maltare & Vahora (2023): Used diverse data sources to improve AQI prediction in Ahmedabad.

  • Some studies (e.g., Li et al.) offer broader overviews but lack specific extraction method details.

6. Neural Networks for Classification

• Neural networks (NNs), particularly deep learning models, are increasingly used for air pollution prediction.

• Applications include:

  • Ravindran et al. (2023): Used NNs to predict AQI in Visakhapatnam.

  • Rakholia et al. (2023): Used multi-output NN models for regional predictions.

  • Taheri & Razbin (2021): Applied NNs for indoor CO? prediction.

  • Varade et al. (2023): Proposed IoT-NN integration for smart cities.

• Studies generally focus on NN effectiveness but often lack detailed architectural discussions.

Conclusion

The survey paper focuses on the current state of research, challenges, and future possibilities for air pollution prediction using machine learning. Machine learning has significantly improved air pollution prediction by combining various methodologies and data sources. Although it remains challenging due to data unpredictability and various component integration, emerging technologies promise to increase real-time management and prediction accuracy. Future research should address these difficulties and explore innovative approaches to improving air quality management and prediction. Machine learning has improved air pollution prediction by providing sophisticated methods for modelling and forecasting pollution levels. Despite the challenges, ongoing improvements in algorithms, data integration, and new technologies promise to improve air quality management and prediction accuracy. Future research will push the boundaries of what is possible, aiming to develop robust and valuable models for real-world applications.

References

[1] Al-Janabi, S., Mohammad, M., & Al-Sultan, A. (2020). A new method for prediction of air pollution based on intelligent computation. Soft Computing, 24(1), 661-680. https://doi.org/10.1007/s00500-019-03972-6 [2] Aram, S. A., Nketiah, E. A., Saalidong, B. M., Wang, H., Afitiri, A. R., Akoto, A. B., & Lartey, P. O. (2024). Machine learning-based prediction of air quality index and air quality grade: A comparative analysis. International Journal of Environmental Science and Technology, 21(2), 1345-1360. https://doi.org/10.1007/s13762-023-04523-4 [3] Calatayud, V., Diéguez, J. J., Agathokleous, E., & Sicard, P. (2023). Machine learning model to predict vehicle electrification impacts on urban air quality and related human health effects. Environmental Research, 228, 115835. [4] Castelli, M., Clemente, F. M., Popovi?, A., Silva, S., & Vanneschi, L. (2020). A machine learning approach to predict air quality in California. Complexity, 2020(1), 8049504. [5] Chang, Y. S., Chiao, H. T., Abimannan, S., Huang, Y. P., Tsai, Y. T., & Lin, K. M. (2020). An LSTM-based aggregated model for air pollution forecasting. Atmospheric Pollution Research, 11(8), 1451-1463. [6] Gokul, P. R., Mathew, A., Bhosale, A., & Nair, A. T. (2023). Using artificial intelligence techniques, spatiotemporal air quality analysis, and PM2. 5 predictions over Hyderabad City, India. Ecological Informatics, 76, 102067. [7] Hardini, M., Sunarjo, R. A., Asfi, M., Chakim, M. H. R., & Sanjaya, Y. P. A. (2023). They are predicting air quality index using ensemble machine learning. ADI Journal on Recent Innovation, 5(1Sp), 78-86. https://doi.org/10.46799/adijri.v5i1sp.290. [8] Harishkumar, K. S., Yogesh, K. M., & Gad, I. (2020). Forecasting air pollution particulate matter (PM2. 5) using machine learning regression models. Procedia Computer Science, 171, 2057-2066. [9] Kumar, K., & Pande, B. P. (2023). Air pollution prediction with machine learning: A case study of Indian cities. International Journal of Environmental Science and Technology, 20(5), 5333-5348. https://doi.org/10.1007/s13762-023-04827-4. [10] Lavanya, P., Reddy, I. S., & Selvakumar, V. (2024). Long-range radio technology implementation on the Internet of Things to detect particulate matter at the community level and predict using a machine learning approach. Engineered Science, 29, 1119. https://doi.org/10.30919/es8d1119. [11] Li, Y., Sha, Z., Tang, A., Goulding, K., & Liu, X. (2023). The application of machine learning to air pollution research: A bibliometric analysis. Ecotoxicology and Environmental Safety, 257, 114911. https://doi.org/10.1016/j.ecoenv.2023.114911. [12] Liu, Q., Cui, B., & Liu, Z. (2024). Air quality class prediction using machine learning methods based on monitoring data and secondary modelling. Atmosphere, 15(5), 553. https://doi.org/10.3390/atmos15050553. [13] Liu, X., Lu, D., Zhang, A., Liu, Q., & Jiang, G. (2022). Data-driven machine learning in environmental pollution: gains and problems. Environmental science & technology, 56(4), 2124-2133. [14] Ma, J., Li, Z., Cheng, J. C., Ding, Y., Lin, C., & Xu, Z. (2020). Air quality prediction at new stations using spatially transferred bi-directional long short-term memory network. Science of The Total Environment, 705, 135771. https://doi.org/10.1016/j.scitotenv.2019.135771. [15] Ma, J., Yu, Z., Qu, Y., Xu, J., & Cao, Y. (2020). Application of the XGBoost machine learning method in PM2.5 prediction: A case study of Shanghai. Aerosol and Air Quality Research, 20(1), 128-138. https://doi.org/10.4209/aaqr.2019.05.0208. [16] Maltare, N. N., & Vahora, S. (2023). Air Quality Index prediction using machine learning for Ahmedabad city. Digital Chemical Engineering, 7, 100093. https://doi.org/10.1016/j.diche.2023.100093. [17] Mampitiya, L., Rathnayake, N., Leon, L. P., Mandala, V., Azamathulla, H. M., Shelton, S., ... & Rathnayake, U. (2023). Machine learning techniques to predict the air quality using meteorological data in two urban areas in Sri Lanka. Environments, 10(8), 141. [18] Mampitiya, L., Rathnayake, N., Leon, L. P., Mandala, V., Azamathulla, H. M., Shelton, S., ... & Rathnayake, U. (2023). Machine learning techniques to predict the air quality using meteorological data in two urban areas in Sri Lanka. Environments, 10(8), 141. [19] Masood, A., & Ahmad, K. (2021). A review on emerging artificial intelligence (AI) techniques for air pollution forecasting: Fundamentals, application and performance. Journal of Cleaner Production, 322, 129072. https://doi.org/10.1016/j.jclepro.2021.129072 [20] Matthaios, V. N., Knibbs, L. D., Kramer, L. J., Crilley, L. R., & Bloss, W. J. (2024). Predicting real-time within-vehicle air pollution exposure with mass-balance and machine learning approaches using on-road and air quality data. Atmospheric Environment, 318, 120233. https://doi.org/10.1016/j.atmosenv.2024.120233 [21] Méndez, M., Merayo, M. G., & Núñez, M. (2023). Machine learning algorithms to forecast air quality: a survey. Artificial Intelligence Review, 56(9), 10031-10066. [22] Rakholia, R., Le, Q., Ho, B. Q., Vu, K., & Carbajo, R. S. (2023). Multi-output machine learning model for regional air pollution forecasting in Ho Chi Minh City, Vietnam. Environment International, 173, 107848. https://doi.org/10.1016/j.envint.2023.107848. [23] Ravindran, G., Hayder, G., Kanagarathinam, K., Alagumalai, A., & Sonne, C. (2023). Air quality prediction by machine learning models: A predictive study on the Indian coastal city of Visakhapatnam. Chemosphere, 338, 139518. https://doi.org/10.1016/j.chemosphere.2023.139518. [24] Ravindra, K., Bahadur, S. S., Katoch, V., Bhardwaj, S., Kaur-Sidhu, M., Gupta, M., & Mor, S. (2023). Application of machine learning approaches to predict the impact of ambient air pollution on outpatient visits for acute respiratory infections. Science of The Total Environment, 858, 159509. https://doi.org/10.1016/j.scitotenv.2023.159509. [25] Stirnberg, R., Cermak, J., Kotthaus, S., Haeffelin, M., Andersen, H., Fuchs, J., ... & Favez, O. (2021). Meteorology-driven variability of air pollution (PM 1) revealed with explainable machine learning. Atmospheric Chemistry and Physics, 21(5), 3919-3948. [26] Suthar, G., Kaul, N., Khandelwal, S., & Singh, S. (2024). Predicting land surface temperature and examining its relationship with air pollution and urban parameters in Bengaluru: A machine learning approach. Urban Climate, 53, 101830. https://doi.org/10.1016/j.uclim.2024.101830. [27] Taheri, S., & Razban, A. (2021). Learning-based CO2 concentration prediction: Application to indoor air quality control using demand-controlled ventilation. Building and Environment, 205, 108164. https://doi.org/10.1016/j.buildenv.2021.108164 [28] Tang, D., Zhan, Y., & Yang, F. (2024). A review of machine learning for modelling air quality: Overlooked but important issues. Atmospheric Research, 107261. https://doi.org/10.1016/j.atmosres.2024.107261 [29] Varade, H. P., Bhangale, S. C., Thorat, S. R., Khatkale, P. B., Sharma, S. K., & William, P. (2023, May). The framework of air pollution assessment in smart cities using IoT with machine learning approach. In 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC) (pp. 1436-1441). IEEE. https://doi.org/10.1109/ICAAIC58029.2023.10217567. [30] Veeranjaneyulu, R., Boopathi, S., Kumari, R. K., Vidyarthi, A., Isaac, J. S., & Jaiganesh, V. (2023, May). Air quality improvement and optimisation using machine learning techniques. In 2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI) (pp. 1-6). IEEE. https://doi.org/10.1109/ACCAI55650.2023.10157934. [31] Wang, S., McGibbon, J., & Zhang, Y. (2024). Predicting high-resolution air quality using machine learning: Integration of large eddy simulation and urban morphology data. Environmental Pollution, 344, 123371. https://doi.org/10.1016/j.envpol.2024.123371. [32] William, P., Paithankar, D. N., Yawalkar, P. M., Korde, S. K., Rajendra, A., & Raksha, D. S. (2023, January). Divination of air quality assessment using ensembling machine learning approach. In 2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF) (pp. 1-10). IEEE.

Copyright

Copyright © 2025 Mrs. P. Umasanthiya, Dr. Marrynal S. Eastaff. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.