Estimation of PM2.5 as a Harmful Environmental Hazard in Tehran by Fusion of MODIS Aerosol Products through a Machine Learning Approach

Document Type : Research Article


1 MA in Reomte Sensing, University of Isfahan, Isfahan, Iran

2 Assistant Professor in Geomatics, University of Isfahan, Isfahan, Iran


Air pollution is one of the most harmful natural hazards in Tehran metropolitan. Particles with a diameter of less than 2.5 micrometers (PM2.5) as one of the most harmful pollutants have endangered the health of people living in Tehran. One of the PM2.5 estimation techniques is the use of Aerosol Optical Depth (AOD) products derived from satellite observations. Various AOD products are retrieved with different algorithms that do not have the same accuracy and spatial resolution. Due to the differences in many assumptions and approximations adopted in the AOD retrieval process, the generated AOD products involve uncertainties. This issue reduces the accuracy of PM2.5 concentration estimation. The purpose of this study was to investigate the possibility of fusing AOD products obtained from MODIS sensor observations (retrieved by Deep Blue and Dark Target algorithms) to estimate PM2.5 more accurately. First, the performance of different machine learning algorithms in estimating PM2.5 from AOD data was evaluated. As a result, the XGBoost algorithm with the highest performance was selected as the base model for PM2.5 estimation. Then, the AOD products were fused using a weighted averaging based on the retrieval quality of the primary products. Finally, the fused AOD product along with meteorological data were employed to estimate PM2.5 using XGboost. The results demonstrated that the accuracy of PM2.5 estimation from the fused AOD product is better than when the AOD products are used individually (= 0.77, MAE = 7.00 , RMSE = 9.59 ). Thus, the retrieval quality of AOD products will lead to more accurate estimation of PM2.5 in the end.

Graphical Abstract

Estimation of PM2.5 as a Harmful Environmental Hazard in Tehran by Fusion of MODIS Aerosol Products through a Machine Learning Approach


Anderson, L. O., Malhi, Y., Aragão, L. E., Ladle, R., Arai, E., Barbier, N., & Phillips, O. (2010). Remote sensing detection of droughts in Amazonian forest canopies. New Phytologist, 187(3), 733-750. doi:
Bagheri, H. (2022). A machine learning-based framework for high resolution mapping of PM2.5 in Tehran, Iran, using MAIAC AOD data. Advances in Space Research, 69(9), 3333-3349. doi:
Bagheri, H. (2023). Using deep ensemble forest for high-resolution mapping of PM2. 5 from MODIS MAIAC AOD in Tehran, Iran. Environmental Monitoring and Assessment, 195(3), 377. doi:
Bagheri, H., Sadeghian, S., & Sadjadi, S. Y. (2014). The Assessment of using an Intelligent Algorithm for the Interpolation of Elevation in the DTM Generation. Photogrammetrie-Fernerkundung-Geoinformation, 197-208. doi:
Bagheri, H., Schmitt, M., d’Angelo, P., & Zhu, X. X. (2018). A framework for SAR-optical stereogrammetry over urban areas. ISPRS journal of photogrammetry and remote sensing, 146, 389-408. doi:
Bagheri, H., Schmitt, M., & Zhu, X. X. (2017). Uncertainty assessment and weight map generation for efficient fusion of TanDEM-X and Cartosat-1 DEMs. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42(1/W1)), 433-439. doi:
Bagheri, H., Schmitt, M., & Zhu, X. X. (2018). Fusion of TanDEM-X and Cartosat-1 elevation data supported by neural network-predicted weight maps. ISPRS journal of photogrammetry and remote sensing, 144, 285-297. doi:
Bharath Ramsundar & Reza Bosagh Zadeh. (2018). TensorFlow for Deep Learning (Rachel Roumeliotis & Alicia Young Ed. first ed. Vol. 16802 KB).
Castanedo, F. (2013). A review of data fusion techniques. The Scientific World Journal, 2013, 704504. doi:
Chang, C.-C., & Lin, C.-J. (2011). LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3), 1-27. doi: doi/10.1145/ 1961189.1961199
Chen, N., Yang, M., Du, W., & Huang, M. (2021). PM2.5 estimation and spatial-temporal pattern analysis based on the modified support vector regression model and the 1 km resolution MAIAC AOD in Hubei, China. ISPRS International Journal of Geo-Information, 10(1), 31. doi:
Dark Target aerosol produact user's guid (2020). In: NASA.
Gogikar, P., Tripathy, M. R., Rajagopal, M., Paul, K. K., & Tyagi, B. (2021). PM2.5 estimation using multiple linear regression approach over industrial and non-industrial stations of India. Journal of Ambient Intelligence and Humanized Computing, 12(2), 2975-2991. doi:
Gupta, P., & Christopher, S. A. (2009). Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: Multiple regression approach. Journal of Geophysical Research: Atmospheres, 114(D14). doi:
Habibi, R., Alesheikh, A. A., Mohammadinia, A., & 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), 270. doi:
Hall, D. L., & Llinas, J. (1997). An introduction to multisensor data fusion. Proceedings of the IEEE, 85(1), 6-23. doi:
Han, B., Ding, H., Ma, Y., & Gong, W. (2017). Improving retrieval accuracy for areosol optical depth by fusiom of MODIS and CALIOP data. Tehnicki vjesnik/Technical Gazette, 24(3). doi:
Hsu, N., Jeong, M. J., Bettenhausen, C., Sayer, A., Hansell, R., Seftor, C., . . . Tsay, S. C. (2013). Enhanced Deep Blue aerosol retrieval algorithm: The second generation. Journal of Geophysical Research: Atmospheres, 118(16), 9296. doi:
Hu, X., Waller, L. A., Lyapustin, A., Wang, Y., Al-Hamdan, M. Z., Crosson, W. L., . . . Puttaswamy, S. J. (2014). Estimating ground-level PM2.5 concentrations in the Southeastern United States using MAIAC AOD retrievals and a two-stage model. Remote Sensing of Environment, 140, 220-232. doi:
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:
Jung, C.-R., Chen, W.-T., & Nakayama, S. F. (2021). A national-scale 1-km resolution PM2.5 estimation model over japan using maiac aod and a two-stage random forest model. Remote Sensing, 13(18), 3657. doi:
Khaleghi, B., Khamis, A., Karray, F. O., & Razavi, S. N. (2013). Multisensor data fusion: A review of the state-of-the-art. Information Fusion, 14(1), 28-44. doi: 10.1016/ j.inffus. 2011.08.001
Kianian, B., Liu, Y., & Chang, H. H. (2021). Imputing satellite-derived aerosol optical depth using a multi-resolution spatial model and random forest for PM2.5 prediction. Remote Sensing, 13(1), 126. doi:
Li, L. (2020). A robust deep learning approach for spatiotemporal estimation of satellite AOD and PM2.5. Remote Sensing, 12(2), 264. doi:
Liao, Q., Jin, W., Tao, Y., Qu, J., Li, Y., & Niu, Y. (2020). Health and Economic Loss Assessment of PM2. 5 Pollution during 2015–2017 in Gansu Province, China. International Journal of Environmental Research and Public Health, 17(9), 3253. doi:https:// 10.3390/ ijerph1 7093253
Liu, N., Zou, B., Feng, H., Wang, W., Tang, Y., & Liang, Y. (2019). Evaluation and comparison of multiangle implementation of the atmospheric correction algorithm, Dark Target, and Deep Blue aerosol products over China. Atmospheric Chemistry and Physics, 19(12), 8243-8268. doi:
Luo, H., Guan, Q., Lin, J., Wang, Q., Yang, L., Tan, Z., & Wang, N. (2020). Air pollution characteristics and human health risks in key cities of northwest China. Journal of Environmental Management, 269, 110791. doi:https:// 10.1016/ j.jenvman. 2020. 110791
Meng, T., Jing, X., Yan, Z., & Pedrycz, W. (2020). A survey on machine learning for data fusion. Information Fusion, 57, 115-129. doi:
Mirzaei, A., Bagheri, H., & Sattari, M. (2023). Data level and decision level fusion of satellite multi-sensor AOD retrievals for improving PM2. 5 estimations, a study on Tehran. Earth Science Informatics, 16(1), 753-771. doi:
Nabavi, S. O., Haimberger, L., & 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), 889-903. doi:https:// 10.1016/ j.apr.2018.12.017
Ni, X., Cao, C., Zhou, Y., Cui, X., & P Singh, R. (2018). Spatio-temporal pattern estimation of PM2. 5 in Beijing-Tianjin-Hebei Region based on MODIS AOD and meteorological data using the back propagation neural network. Atmosphere, 9(3), 105. doi:https:// 10.3390/atmos9030105
Pashayi, M., & Satari, M. (2022). Improvement of spatial-temporal resolution of aerosol profile by using multi-source satellite data over the Persian Gulf. Atmospheric Environment, 119410. doi:
Popov, S., Morozov, S., & Babenko, A. (2019). Neural oblivious decision ensembles for deep learning on tabular data. arXiv preprint arXiv:1909.06312. doi: 10.48550/ arXiv.1909.06312
Qi, Y., Li, Q., Karimian, H., & Liu, D. (2019). A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory. Science of the Total Environment, 664, 1-10. doi:
Remer, L., Mattoo, S., Levy, R., & Munchak, L. (2013). MODIS 3 km aerosol product: algorithm and global perspective. Atmospheric Measurement Techniques, 6(7), 1829-1844. doi:
Sayer, A., Munchak, L., Hsu, N., Levy, R., Bettenhausen, C., & Jeong, M. J. (2014). MODIS Collection 6 aerosol products: Comparison between Aqua's Deep Blue, Dark Target, and “merged” data sets, and usage recommendations. Journal of Geophysical Research: Atmospheres, 119(24), 13,965-913,989. doi:
Shwartz-Ziv, R., & Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81, 84-90. doi:
Singer, A., Zobeck, T., Poberezsky, L., & Argaman, E. (2003). The PM10 and PM2.5 dust generation potential of soils/sediments in the Southern Aral Sea Basin, Uzbekistan. Journal of Arid Environments, 54(4), 705-728. doi:
Stafoggia, M., Bellander, T., Bucci, S., Davoli, M., De Hoogh, K., De'Donato, F., . . . Renzi, M. (2019). Estimation of daily PM10 and PM2.5 concentrations in Italy, 2013–2015, using a spatiotemporal land-use random-forest model. Environment International, 124, 170-179. doi:
Tang, Q., Bo, Y., & Zhu, Y. (2016). Spatiotemporal fusion of multiple‐satellite aerosol optical depth (AOD) products using Bayesian maximum entropy method. Journal of Geophysical Research: Atmospheres, 121(8), 4034-4048. doi:
Tsai, T.-C., Jeng, Y.-J., Chu, D. A., Chen, J.-P., & Chang, S.-C. (2011). Analysis of the relationship between MODIS aerosol optical depth and particulate matter from 2006 to 2008. Atmospheric Environment, 45(27), 4777-4788. doi:https:// 10.1016/ j.atmosenv. 2009.10. 006
Wang, Y., Yuan, Q., Shen, H., Zheng, L., & Zhang, L. (2020). Investigating multiple aerosol optical depth products from MODIS and VIIRS over Asia: Evaluation, comparison, and merging. Atmospheric Environment, 230, 117548. doi:https:// 10.1016/ j.atmosenv. 2020. 117548
Wang, Z., Chen, L., Tao, J., Zhang, Y., & Su, L. (2010). Satellite-based estimation of regional particulate matter (PM) in Beijing using vertical-and-RH correcting method. Remote Sensing of Environment, 114(1), 50-63. doi:
Wei, X., Chang, N.-B., Bai, K., & Gao, W. (2020). Satellite remote sensing of aerosol optical depth: Advances, challenges, and perspectives. Critical Reviews in Environmental Science and Technology, 50(16), 1640-1725. doi:
Xia, X., Zhao, B., Zhang, T., Wang, L., Gu, Y., Liou, K.-N., . . . Huang, Y. (2021). Satellite-Derived Aerosol Optical Depth Fusion Combining Active and Passive Remote Sensing Based on Bayesian Maximum Entropy. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-13. doi:
Xiao, Q., Chang, H. H., Geng, G., & Liu, Y. (2018). An ensemble machine-learning model to predict historical PM2.5 concentrations in China from satellite data. Environmental science & technology, 52(22), 13260-13269. doi:
Xu, H., Guang, J., Xue, Y., De Leeuw, G., Che, Y., Guo, J., . . . Wang, T. (2015). A consistent aerosol optical depth (AOD) dataset over mainland China by integration of several AOD products. Atmospheric Environment, 114, 48-56. doi: 10.1016/ j.atmosenv. 2015. 05.023
Xu, H., Xue, Y., Guang, J., Li, Y., Yang, L., Hou, T., . . . Chen, Z. (2012). A semi-empirical optical data fusion technique for merging aerosol optical depth over China. Paper presented at the 2012 IEEE International Geoscience and Remote Sensing Symposium.
Yang, Q., Yuan, Q., Li, T., Shen, H., & Zhang, L. (2017). The relationships between PM2.5 and meteorological factors in China: seasonal and regional variations. International Journal of Environmental Research and Public Health, 14(12), 1510. doi: 10.3390%2 Fijerph14121510
You, W., Zang, Z., Zhang, L., Li, Y., Pan, X., & Wang, W. (2016). National-scale estimates of ground-level PM2.5 concentration in China using geographically weighted regression based on 3 km resolution MODIS AOD. Remote Sensing, 8(3), 184. doi:https:// 10.3390/rs8030184
Zamani Joharestani, M., Cao, C., Ni, X., Bashir, B., & Talebiesfandarani, S. (2019). PM2.5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data. Atmosphere, 10(7), 373. doi:
Zhao, C., Wang, Q., Ban, J., Liu, Z., Zhang, Y., Ma, R., . . . Li, T. (2020). Estimating the daily PM2.5 concentration in the Beijing-Tianjin-Hebei region using a random forest model with a 0.01°× 0.01° spatial resolution. Environment International, 134, 105297. doi:https:// 10.1016/j.envint.2019.105297
Zhu, X. X., Hu, J., Qiu, C., Shi, Y., Kang, J., Mou, L., . . . Huang, R. (2020). So2Sat LCZ42: A benchmark data set for the classification of global local climate zones [Software and Data Sets]. IEEE Geoscience and Remote Sensing Magazine, 8(3), 76-89. doi:https://d 10.1109/ MGRS.2020.2964708