[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Current Issue :: Archive :: Search :: Submit :: Contact ::
Main Menu
Home::
Browse::
Journal Info::
Guide for Authors::
Submit Manuscript::
Articles archive::
For Reviewers::
Contact us::
Site Facilities::
Reviewers::
::
Search in website

Advanced Search
..
Receive site information
Enter your Email in the following box to receive the site news and information.
..
:: Volume 16, Issue 1 (9-2026) ::
JGST 2026, 16(1): 17-34 Back to browse issues page
Spatiotemporal modeling of PM2.5 in the city of Tehran using multi-source data and explainable machine learning
Parastoo Pilehforooshha * , Hossein Ahmadi Riabi
Abstract:   (5 Views)
Fine particulate matter (PM₂.₅) air pollution is one of the most critical environmental and public health challenges in metropolitan areas. Although machine learning models have been widely applied for PM₂.₅ prediction, most previous studies have examined spatial and temporal effects separately, with limited attention to the simultaneous evaluation of spatiotemporal scales, interactions among influential variables, and model interpretability. In this study, an explainable machine learning framework was developed for spatiotemporal PM₂.₅ modeling in Tehran, Iran. To this end, air quality monitoring data were integrated with meteorological variables, temporal features, land use and land cover characteristics, urban morphology, spatiotemporal neighborhood features, and interaction features. The performance of Decision Tree, Random Forest, and XGBoost models was evaluated at two spatial resolutions (500 m and 1000 m) and two temporal scales (weekly and monthly). In addition, SHAP (SHapley Additive exPlanations) was employed to interpret model behavior and analyze feature importance at both global and local levels. The results showed that XGBoost achieved the best performance at the 1000 m spatial resolution and weekly temporal scale, with an R² of 0.557. Meteorological variables, spatiotemporal neighborhood features, and interaction features were identified as the most influential predictors of PM₂.₅, while SHAP analysis revealed substantial spatial heterogeneity in their effects. These findings demonstrate that jointly evaluating spatial and temporal scales, together with incorporating interaction features and explainable machine learning, can improve PM₂.₅ prediction and enhance understanding of the factors driving air pollution, thereby supporting air quality management and urban planning.
Article number: 2
Keywords: PM2.5, spatiotemporal modeling, multi-source data, machine learning, SHAP.
Full-Text [PDF 1853 kb]   (3 Downloads)    
Type of Study: Research | Subject: GIS
Received: 2026/04/8 | Accepted: 2026/09/6
References
1. World Health Organization. (2022, April 4). Billions of people still breathe unhealthy air: new WHO data. https://www.who.int/news/item/04-04-2022-billions-of-people-still-breathe-unhealthy-air-new-who-data
2. Naddafi, K., Hassanvand, M. S., Yunesian, M., Momeniha, F., Nabizadeh, R., Faridi, S., & Gholampour, A. (2012). Health impact assessment of air pollution in megacity of Tehran, Iran. Iranian journal of environmental health science & engineering, 9(1), 28. [DOI:10.1186/1735-2746-9-28]
3. Shahbazi, H., Reyhanian, M., Hosseini, V., & Afshin, H. (2016). The relative contributions of mobile sources to air pollutant emissions in Tehran, Iran: an emission inventory approach. Emission control science and technology, 2(1), 44-56. [DOI:10.1007/s40825-015-0031-x]
4. Mohammadi, F., Teiri, H., Hajizadeh, Y., Abdolahnejad, A., & Ebrahimi, A. (2024). Prediction of atmospheric PM2. 5 level by machine learning techniques in Isfahan, Iran. Scientific Reports, 14(1), 2109. [DOI:10.1038/s41598-024-52617-z]
5. Zhalehdoost A, Taleai M. (2025). Unravelling the importance of spatial and temporal resolutions in modeling urban air pollution using a machine learning approach. Scientific Reports. Jul 29;15(1):27708. [DOI:10.1038/s41598-025-13639-3]
6. Tella, A., & Balogun, A.-L. (2022). GIS-based air quality modelling: Spatial prediction of PM10 for Selangor State, Malaysia using machine learning algorithms. Environmental Science and Pollution Research, 29(57), 86109-86125. [DOI:10.1007/s11356-021-16150-0]
7. Sayeed, A., Choi, Y., Eslami, E., Lops, Y., Roy, A., & Jung, J. (2020). Using a deep convolutional neural network to predict 2017 ozone concentrations, 24 hours in advance. Neural Networks, 121, 396-408. [DOI:10.1016/j.neunet.2019.09.033]
8. Delavar, M.R., Gholami, A., Shiran, G.R., Rashidi, Y., Nakhaeizadeh, G.R., Fedra, K. and Hatefi Afshar, S. (2019). A novel method for improving air pollution prediction based on machine learning approaches: a case study applied to the capital city of Tehran. ISPRS International Journal of Geo-Information, 8(2), p.99. [DOI:10.3390/ijgi8020099]
9. Huang, C.-J., & Kuo, P.-H. (2018). A deep CNN-LSTM model for particulate matter (PM2. 5) forecasting in smart cities. Sensors, 18(7), 2220. [DOI:10.3390/s18072220]
10. Habibi, R., Alesheikh, A.A., Mohammadinia, A. and Sharif, M. (2017). An assessment of spatial pattern characterization of air pollution: A case study of CO and PM2. 5 in Tehran, Iran. ISPRS international journal of Geo-information, 6(9), p.270. [DOI:10.3390/ijgi6090270]
11. Rybarczyk, Y., & Zalakeviciute, R. (2018). Machine learning approaches for outdoor air quality modelling: A systematic review. Applied Sciences, 8(12), 2570. [DOI:10.3390/app8122570]
12. Nabavi, S.O., Haimberger, L. and Abbasi, E. (2019). Assessing PM2. 5 concentrations in Tehran, Iran, from space using MAIAC, deep blue, and dark target AOD and machine learning algorithms. Atmospheric Pollution Research, 10(3), pp.889-903. [DOI:10.1016/j.apr.2018.12.017]
13. Kaviani Rad, A. K., Shamshiri, R. R., Naghipour, A., Razmi, S.-O., Shariati, M., Golkar, F., & Balasundram, S. K. (2022). Machine learning for determining interactions between air pollutants and environmental parameters in three cities of Iran. Sustainability, 14(13), 8027. [DOI:10.3390/su14138027]
14. Makhdoomi, A., Sarkhosh, M. and Ziaei, S. (2025). PM2. 5 concentration prediction using machine learning algorithms: an approach to virtual monitoring stations. Scientific Reports, 15(1), p.8076. [DOI:10.1038/s41598-025-92019-3]
15. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). " Why should I trust you?" Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. [DOI:10.18653/v1/N16-3020]
16. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
17. Liu, X., & Su, H. (2025). Unraveling the complex relationships between urban land use pattern and air quality: Evidence from GBDT-SHAP analysis. Urban Climate, 64, 102711. [DOI:10.1016/j.uclim.2025.102711]
18. Abbasi, M. T., Alesheikh, A. A., & Rezaie, F. (2025). A Lightweight Spatiotemporal Graph Framework Leveraging Clustered Monitoring Networks and Copula-Based Pollutant Dependency for PM2. 5 Forecasting. Land, 14(8), 1589. [DOI:10.3390/land14081589]
19. Burrough, P. A., & McDonnell, R. A. (1998). Principles of Geographical Information Systems. Oxford University Press.
20. Li, J., & Heap, A. D. (2014). A review of spatial interpolation methods for environmental scientists. Geoscience Australia. [DOI:10.1016/j.envsoft.2013.12.008]
21. Xu, W., Jin, X., Liu, M., Ma, Z. and Zhou, Y. (2021). Analysis of spatiotemporal variation of PM2. 5 and its relationship to land use in China. Atmospheric Pollution Research, 12(9), p.101151. [DOI:10.1016/j.apr.2021.101151]
Send email to the article author

Add your comments about this article
Your username or Email:

CAPTCHA


XML   Persian Abstract   Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Pilehforooshha P, Ahmadi Riabi H. Spatiotemporal modeling of PM2.5 in the city of Tehran using multi-source data and explainable machine learning. , JGST. 2026; 16 (1) : 2
URL: http://jgst.issgeac.ir/article-1-1254-en.html


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 16, Issue 1 (9-2026) Back to browse issues page
نشریه علمی علوم و فنون نقشه برداری Journal of Geomatics Science and Technology