Original Research

Prediction of particulate matter PM2.5 level in the air of Islamabad, Pakistan by using machine learning and deep learning approaches

Abstract

Introduction: Air pollution is a significant global health challenge, contributing to the deaths of millions of people annually. Among these pollutants, Particulate Matter (PM2.5) is the most harmful to the respiratory system causing serious health problems. This study focused on predicting PM2.5 in the air of Islamabad, capital of Pakistan by using machine learning and deep learning models.
Materials and methods: Two machine learning models (Decision Tree and Random Forest) and four deep learning models including Multi-Layer Neural Network (MLNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU) are used in the study. Each model's performance was assessed by using statistical indicators including coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Relative Root Mean Square Error (RRMSE). These models are also ranked based on their performance by compromise programming technique.
Results: Machine learning models performed better in the training phase by achieving higher R2 values of 0.98 and 0.97 but couldn’t maintain the same performance in the testing phase. Whereas the deep learning models
performed best in both the training and testing phases. MLNN model attained higher R2 value of 0.98 in training and 0.88 in testing and is evaluated as top-ranked prediction model in predicting particulate matter PM2.5. Whereas, LSTM, GRU, RNN, Decision Tree, and Random Forest are placed at the 2nd, 3rd, 4th, 5th, and 6th positions having R2 values of 0.86, 0.87, 0.82, 0.99, and 0.97 during training and 0.71, 0.69, 0.69, 0.75, and 0.85 respectively during testing.
Conclusion: Deep learning models, especially MLNN, showed strong performance in predicting PM2.5 as compared to the machine learning models.

1. Gul H, Das B. The Impacts of Air Pollution on Human Health and Well-Being: A Comprehensive Review. Journal of Environmental Impact and Management Policy. 2023:1-11.
2. Wang C, Miao Z, Chen X, Cheng Y. Factors affecting changes of greenhouse gas emissions in Belt and Road countries. Renewable and Sustainable Energy Reviews. 2021;147:111220.
3. Wang Q, Liu S. The Effects and Pathogenesis of PM2.5 and Its Components on Chronic Obstructive Pulmonary Disease. Int J Chron Obstruct Pulmon Dis. 2023;18:493-506.
4. Tran HM, Tsai F-J, Lee Y-L, Chang J-H, Chang L-T, Chang T-Y, et al. The impact of air pollution on respiratory diseases in an era of climate change: A review of the current evidence. Science of The Total Environment. 2023;898:166340.
5. Samad A, Garuda S, Vogt U, Yang B. Air pollution prediction using machine learning techniques – An approach to replace existing monitoring stations with virtual monitoring stations. Atmospheric Environment. 2023;310:119987.
6. Zhang Z, Zhang S, Chen C, Yuan J. A systematic survey of air quality prediction based on deep learning. Alexandria Engineering Journal. 2024;93:128-41.
7. Silibello C, Bolignano A, Sozzi R, Gariazzo C. Application of a chemical transport model and optimized data assimilation methods to improve air quality assessment. Air Quality Atmosphere & Health. 2014;7.
8. Pokharel S, Ghimire P. Data-driven MLmodels for accurate prediction of energy consump- tion in a low-energy house: A comparative study of XGBoost, Random Forest, Decision Tree, and Support Vector Machine. Journal of Innovations in Engineering Education. 2023;6:12-20.
9. Zhou S, Wang W, Zhu L, Qiao Q, Kang Y. Deep-learning architecture for PM2.5 concentration prediction: A review. Environmental Science and Ecotechnology. 2024;21:100400.
10. Venkateswaran D, Cho Y. Efficient solar power generation forecasting for greenhouses: A hybrid deep learning approach. Alexandria Engineering Journal. 2024;91:222-36.
11. Kamali Mohammadzadeh A, Salah H, Jahanmahin R, Hussain AEA, Masoud S, Huang Y. Spatiotemporal integration of GCN and E-LSTM networks for PM2.5 forecasting. Machine Learning with Applications. 2024;15:100521.
12. Gulia S, Khanna I, Shukla K, Khare M. Ambient air pollutant monitoring and analysis protocol for low and middle income countries: An element of comprehensive urban air quality management framework. Atmospheric Environment. 2020;222:117120.
13. Rahman A, Usama M, Tahir M, Uppal M. Data driven framework for analysis of air quality landscape for the city of Lahore. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2022;XLVIII-4/W5-2022:167-73.
14. Waqas M, Humphries U, Chueasa B, Wangwongchai A. Artificial Intelligence and Numerical Weather Prediction Models: A Technical Survey. Natural Hazards Research. 2024.
15. Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena. 2020;404:132306.
16. Wang X, Huang T, Zhu K, Zhao X. LSTM-based broad learning system for remaining useful life prediction. Mathematics. 2022;10(12):2066.
17. Zhang J, Du J, Dai L, editors. A gru-based encoder-decoder approach with attention for online handwritten mathematical expression recognition. 2017 14th IAPR international conference on document analysis and recognition (ICDAR); 2017: IEEE.
18. Alkawaz AN, Kanesan J, Khairuddin ASM, Badruddin IA, Kamangar S, Hussien M, et al. Training Multilayer Neural Network Based on Optimal Control Theory for Limited Computational Resources. Mathematics. 2023;11(3):778.
19. Aslan S, Zennaro F, Furlan E, Critto A. Recurrent neural networks for water quality assessment in complex coastal lagoon environments: A case study on the Venice Lagoon. Environmental Modelling & Software. 2022;154:105403.
20. Tyagi A, Rekha G. Challenges of Applying Deep Learning in Real-World Applications. 2020. p. 92-118.
21. LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015;521(7553):436-44.
22. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012;25.
23. Hinton GE, Osindero S, Teh Y-W. A fast learning algorithm for deep belief nets. Neural computation. 2006;18(7):1527-54.
Files
IssueVol 10 No 1 (2025): Winter 2025 QRcode
SectionOriginal Research
Keywords
Long and short-term memory (LSTM); Deep learning; Air quality; Machine learning; Multi-layers neural network (MLNN)
Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
1.
Waqas M, Jan S, Ullah B, Khan A, Rauf A, Niaz Khan B. Prediction of particulate matter PM2.5 level in the air of Islamabad, Pakistan by using machine learning and deep learning approaches. JAPH. 2025;10(1):37-60.