Е-Публикации
Технически университет - София

Abstract: This work is openly licensed via CC BY-NC-ND.In this paper, we introduce a new approach designed to forecast up to 24 hours in advance five air pollutants at construction sites given the temperature as an exogenous variable. The considered pollutants are two particulate matter (PM2.5, PM10) and three gaseous pollutants (NO_2, CO and O_3). The proposed approach employs and compares three well-known predictive model types on forecasting each air pollutant: random forest, feed-forward artificial neural network and transformer architecture. Their performances are evaluated in terms of Root Mean Squared Error on the single pollutants with single-output models. Experimental results, based on data collected from AirQino sensor stations at a real construction site, demonstrate that random forest continues to be a reliable and frequently top-performing choice for long-term forecasting in this context. However, the transformer architecture emerges as a strong alternative, especially well-suited for short-term prediction tasks and scenarios with limited data availability.

References

1. H. Yan, Q. Li, K. Feng and L. Zhang, "The Characteristics pf PM Emissions from Construction Sites During the Earthwork and Foundation Stages: An Empirical Study Evidence", {\it Environ. Sci. Pollut. Res. Int}, vol. 30, no. 22, pp. 62716-62732, 2023, DOI: 10.1007/s11356-023-26494-4
2. Y. Gu, D. K. Henze, M. O. Nawaz, H. Cao and U. J. Wagner, "Sources of PM2.5-Associated Health Risks in Europe and Corresponding Emission-Induced Changes During 2015", GeoHealth, vol. 7, 2023, DOI: 10.1029/2022GH000767
3. J. López, "REPORT on the Implementation of the Ambient Air Quality Directives: Directive 2004/107/EC and Directive 2008/50/EC", Report - A9-0037/2021, 2021
4. Institute for Bioeconomy, CNR, AirQino. [Online]. Available at: https://www.AirQino.it/
5. J. Hong, H. Kang, S. Jung, S. Sung, T. Hong, H.S. Park and D.E. Lee, “An Empirical Analysis of Environmental Pollutants on Building Construction Sites for Determining the Real-Time Monitoring Indices”, Building and Environment, vol. 170, 2020, DOI: 10.1016/j.buildenv.2019.106636
6. K. Liao, X. Huang, H. Dang, Y. Ren, S. Zuo and C. Duan, “Statistical Approaches for Forecasting Primary Air Pollutants: A Review”, Atmosphere, vol. 12, no. 6, 2021, DOI: 10.3390/atmos12060686
7. J. Krall, “Predictive Learning for Air Pollution at Construction Sites Using Multimodal Data”, i3CE’24, Conference Proceedings, Pittsburgh, Pennsylvania, USA, 2024, pp.1-10
8. A. A. Wieser, M. Scherz, A. Passer and H. Kreiner, “Challenges of a Healthy Built Environment: Air Pollution in Construction Industry”, Sustainability, vol. 13, no. 18, 2021, DOI: 10.3390/su131810469
9. A. Biloshchytskyi, A. Kuchansky, Y. Andrashko, A. Neftissov, V. Vatskel, D. Yedilkhan and M. Herych, “Building a Model for Choosing a Strategy for Reducing Air Pollution Based on Data Predictive Analysis”, Eastern-European Journal of Enterprise Technologies, vol. 117, no. 4, 2022, DOI: 10.15587/1729-4061.2022.259323
10. L. Milivojević, S. Mrazovac Kurilić, Z. Božilović, S. Koprivica and O. Krčadinac, “Study of Particular Air Quality and Meteorological Parameters at a Construction Site”, Atmosphere, vol. 14, no. 8, 2023, DOI: 10.3390/atmos14081267
11. Z. Xu, Y. Ran and Z. Rao, “Design and Integration of Air Pollutants Monitoring System for Emergency Management in Construction Site Based on BIM and Edge Computing”, Building and Environment, vol. 211, 2022, DOI: 10.1016/j.buildenv.2021.108725
12. E. Z. Gill, D. Cardone and A. Amelio, “Revolutionizing the Construction Industry by Cutting Edge Artificial Intelligence Approaches: A Review”, Frontiers in Artificial Intelligence, vol. 7, 2024, DOI: 10.3389/frai.2024.1474932
13. M. Mastromatteo and A. Amelio, “A Deep Learning Approach for Predicting Air Pollutants on the Construction Site”, MIPRO’24, Conference Proceedings, Opatija, Croatia, 2024, pp. 2089-2094, DOI: 10.1109/MIPRO60963.2024.10569266
14. E. Z. Gill, A. Amelio, D. Cardone, M. Mastromatteo, P. Cellini, L. Cangelmi, "Integrating Meteorological Data with Artificial Intelligence for Air Quality Prediction on Construction Sites," 24th International Symposium INFOTEH-JAHORINA. INFOTEH 2025, East Sarajevo, Bosnia and Herzegovina, 2025, pp. 1-6, DOI: 10.1109/INFOTEH64129.2025.10959186
15. E. Z. Gill, M. Mastromatteo, L. Cangelmi, P. Cellini, D. Cardone and A. Amelio, "A Comparative Analysis of Artificial Intelligence Methods for Air Quality Prediction on Construction Sites," MIPRO 48th ICT and Electronics Convention, Opatija, Croatia, 2025, pp. 2127-2132, DOI: 10.1109/MIPRO65660.2025.11131894
16. E. Z. Gill, L. Cangelmi, P. Cellini, A. Zaldei, I. R. Draganov, D. Cardone, "Air Pollution Forecasting at Construction Sites: An Intelligent Comparative Framework", 60th International Scientific Conference on Information, Communication and Energy Systems and Technologies(ICEST), Ohrid, North Macedonia, 2025, pp. 1-4, DOI: 10.1109/ICEST66328.2025.11098263
17. S. Berkani, I. Gryech, M. Ghogho, B. Guermah and A. Kobbane, "Data Driven Forecasting Models for Urban Air Pollution: MoreAir Case Study", IEEE Access, vol. 11, pp. 133131-133142, 2023, DOI: 10.1109/ACCESS.2023.3331565
18. R. Rakholia, Q. Le, B. Q. Ho, K. Vu and R. S. Carbajo, "Multi-Output Machine Learning Model for Regional Air Pollution Forecasting in Ho Chi Minh City, Vietnam", Environment International, vol. 173, 2023, DOI:10.1016/j.envint.2023.107848
19. Z. Zhang, C. Johansson, M. Engardt, M. Stafoggia and X. Ma, "Improving 3-day Deterministic air Pollution Forecasts using Machine Learning Algorithms", Atmospheric Chemistry and Physics, vol. 24, no. 2, pp. 807-851, DOI: 10.5194/acp-24-807-2024
20. J. Kalajdjieski, K. Trivodaliev, G. Mirceva, S. Kalajdziski and S. Gievska, "A Complete Air Pollution Monitoring and Prediction Framework", IEEE Access, vol. 11, pp. 88730-88744, DOI: 10.1109/ACCESS.2023.3251346
21. I. Jairi, S. Ben-Othman, L. Canivet and H. Zgaya-Biau, "Enhancing Air Pollution Prediction: A Neural Transfer Learning Approach Across Different Air Pollutants", Environmental Technology & Innovation, vol. 36, 2024, DOI: 10.1016/j.eti.2024.103793
22. Y. Zhang, Q. Sun, J. Liu and O. Petrosian, "Long-Term Forecasting of Air Pollution Particulate Matter (PM2.5) and Analysis of Influencing Factors", Sustainability, vol. 16, no. 1, 2024, DOI: 10.3390/su16010019
23. T. D. Akinosho, M. Bilal, E. T. Hayes, A. Ajayi, A. Ahmed and Z. Khan, "Deep Learning-Based Multi-Target Regression for Traffic-Related Air Pollution Forecasting", Machine Learning with Applications, vol. 12, 2023, DOI: 10.1016/j.mlwa.2023.100474
24. V. Oliveira Santos, P. A. C. Rocha, J. Scott, J. Van Griensven Thé and B. Gharabaghi, "Spatiotemporal Air Pollution Forecasting in Houston-TX: A Case Study for Ozone Using Deep Graph Neural Networks", Atmosphere, vol. 14, 2023, DOI: 10.3390/atmos14020308
25. T. Handhayani, "An Integrated Analysis of Air Pollution and Meteorological Conditions in Jakarta", Scientific Reports, vol. 13, no. 1, 2023, DOI: 10.1038/s41598-023-32817-9
26. M. J. Jiménez-Navarro, M. Lovrić, S. Kecorius, E. K. Nyarko and M. Martínez-Ballesteros, "Explainable Deep Learning on Multi-Target Time Series Forecasting: An Air Pollution use case", Results in engineering, vol. 24, 2024, DOI: 10.1016/j.rineng.2024.103290
27. J. Praveenchandar, K. Venkatesh, B. Mohanraj, M. Prasad and R. Udayakumar, "Prediction of Air Pollution Utilizing an Adaptive Network Fuzzy Inference System with the aid of Genetic Algorithm", Natural and engineering sciences, vol. 9, no. 1, pp. 46-56, 2024, DOI: 10.28978/nesciences.1489228
28. H. A. Nguyen, Q. P. Ha, H. Duc, M. Azzi, N. Jiang, X. Barthelemy and M. Riley, "Long Short-Term Memory Bayesian Neural Network for Air Pollution Forecast", IEEE Access, vol. 11, pp. 35710-35725, 2023, DOI: 10.1109/ACCESS.2023.3265725
29. S. Baniasadi, R. Salehi, S. Soltani, D. Martín, P. Pourmand and E. Ghafourian, "Optimizing Long Short-Term Memory Network for Air Pollution Prediction using a Novel Binary Chimp Optimization Algorithm", Electronics, vol. 12, no. 18, 2023, DOI: 10.3390/electronics12183985
30. F. Fauzi, R. Wasono and I. Kharisudin, "Evaluating Recurrent Neural Networks and Long Short-Term Memory for Air Pollution Forecasting: Mitigating the Impact of Volatile Environmental Factors", Commun. Math. Biol. Neurosci., 2023, Article ID 129
31. Z. He and Q. Guo, "Comparative Analysis of Multiple Deep Learning Models for Forecasting Monthly Ambient PM2.5 Concentrations: A case Study in Dezhou City, China", Atmosphere, vol. 15, no. 12, 2024, DOI: 10.3390/atmos15121432
32. J. Luo and Y. Gong, "Air Pollutant Prediction Based on ARIMA-WOA-LSTM Model", Atmospheric Pollution Research, vol. 14, no. 6, 2023, DOI: 10.1016/j.apr.2023.101761
33. W. Ding and X. Qie, "Prediction of Air Pollutant Concentrations via RANDOM Forest Regressor Coupled with Uncertainty Analysis—A Case Study in Ningxia", Atmosphere, vol. 13, no. 6, 2022,DOI: 10.3390/atmos13060960
34. G. Corani, "Air Quality Prediction in Milan: Feed-Forward Neural Networks, Pruned Neural Networks and Lazy Learning", Ecological Modelling, vol. 185, no. 2–4, pp. 513-529, 2005, DOI: 10.1016/j.ecolmodel.2005.01.008
35. T. Jayanth, A. Manimaran, V. R. K. Reddy and N. Rajashekar, "Enhancing Air Quality Prediction Through Holt–Winters Smoothing and Transformer-BiGRU with Bayesian Optimization", IEEE Access, vol. 13, pp. 180756-180780, 2025, DOI:10.1109/ACCESS.2025.3621231

Issue