SavedAdd your journal

Journals / Karaelmas Fen ve Mühendislik Dergisi / 2026 / Cilt: 15 Sayı: 1

Estimation of Hourly NO2 Concentrations in İzmir’s Atmosphere Using Sentinel-5P Satellite Data and a Machine Learning Approach

Sentinel-5P Uydu Verileri ve Makine Öğrenmesi Yöntemiyle İzmir Atmosferinde Saatlik NO2 Konsantrasyonlarının Tahmini

Efem Bilgiç(DOKUZ EYLÜL ÜNİVERSİTESİ)0000-0002-6855-4750
Tolga Elbir(DOKUZ EYLÜL ÜNİVERSİTESİ)0000-0001-6760-3955
Pages
175–194
Publication Date
2025-04-22
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

It is foreseen that future large-scale modeling studies across Türkiye for other air pollutants will contribute significantly to air pollution analytics and environmental policy development processes.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study, leveraging the potential of remote sensing data and machine learning methods in air quality prediction, aimed to estimate hourly NO2 concentrations obtained from 10 air quality monitoring stations in İzmir between 2022 and 2023.
📊
Key Findings & Data:In this context, the random forest algorithm was applied using Sentinel-5P satellite data, reanalysis products, and digital elevation model parameters.
💡
Conclusion & Impact:It is foreseen that future large-scale modeling studies across Türkiye for other air pollutants will contribute significantly to air pollution analytics and environmental policy development processes.
🔬Design:Modeling & Simulation
📍Scope:2022 Verileri
⚙️Variables:Hava kalitesi tahmini · İzmir · Makine öğrenmesi

Abstract

This study, leveraging the potential of remote sensing data and machine learning methods in air quality prediction, aimed to estimate hourly NO2 concentrations obtained from 10 air quality monitoring stations in İzmir between 2022 and 2023. In this context, the random forest algorithm was applied using Sentinel-5P satellite data, reanalysis products, and digital elevation model parameters. The model’s performance was evaluated using 10-fold cross-validation, with the metrics R2 , index of agreement (IA), root mean square error (RMSE), and mean absolute error (MAE) calculated as 0.71, 0.91, 14.52, and 8.88, respectively. These accuracy values provide a firm reference for national air quality modeling studies. The analysis revealed seasonal and spatial variations influenced the model’s performance. Specifically, the presence of outliers and the impact of seasonal conditions on the accuracy of Sentinel-5P data played a significant role in the performance variations. Feature importance analyses indicated that the most influential parameters in the model’s predictions were vegetation, Sentinel-5P data, albedo, and elevation. This study offers a comprehensive approach for reliably estimating NO2 concentrations in areas where measurement networks are limited and serves as a valuable resource for decision-makers in combating air pollution. It is foreseen that future large-scale modeling studies across Türkiye for other air pollutants will contribute significantly to air pollution analytics and environmental policy development processes.

Özet

Bu çalışmada, hava kalitesi tahmininde uzaktan algılama verilerinin ve makine öğrenmesi yöntemlerinin sunduğu potansiyelden yararlanılarak 2022-2023 yılları arasında İzmir’deki 10 hava kalitesi izleme istasyonundan elde edilen saatlik NO2 konsantrasyonlarının tahmini amaçlanmıştır. Bu kapsamda, Sentinel-5P uydu verileri, yeniden analiz ürünleri ve sayısal yükselti modeli parametreleri kullanılarak rastgele orman algoritması uygulanmıştır. Model performansı, 10 katmanlı çapraz doğrulama yöntemiyle değerlendirilmiş; R2 , uyuşma indeksi (Uİ), kök ortalama kare hatası (KOKH) ve ortalama mutlak hata (OMH) metrikleri sırasıyla 0.71, 0.91, 14.52 ve 8.88 olarak hesaplanmıştır. Bu doğruluk değerleri, ulusal ölçekte hava kalitesi modelleme çalışmalarında güçlü bir referans sunmaktadır. Analiz sonuçları, model performansının mevsimsel ve mekânsal farklılıklardan etkilendiğini ortaya koymuştur. Özellikle uç değerlerin varlığı ve mevsimsel koşulların Sentinel-5P verilerinin doğruluğu üzerindeki etkisi, performans değişikliklerinde önemli bir rol oynamaktadır. Özellik önemi analizleri, model tahminlerinde en etkili parametrelerin vejetasyon, Sentinel-5P verileri, albedo ve yükselti olduğunu göstermiştir. Bu çalışma, mevcut ölçüm ağlarının kısıtlı olduğu bölgelerde NO2 konsantrasyonlarının güvenilir şekilde tahmin edilmesine yönelik yenilikçi bir yaklaşım sunarak, hava kirliliği ile mücadelede karar alıcılar için önemli bir katkı sağlamaktadır. Gelecekte Türkiye genelinde gerçekleştirilecek geniş kapsamlı modelleme çalışmaları ile diğer hava kirleticilerinin tahminine yönelik uygulamaların, hava kirliliği analitiği ve çevresel politika geliştirme süreçlerine önemli katkılar sağlaması öngörülmektedir.

🔖

Cite This Article

Bilgiç, E., Elbir, T. (2025). Estimation of Hourly NO2 Concentrations in İzmir’s Atmosphere Using Sentinel-5P Satellite Data and a Machine Learning Approach. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 15 Sayı: 1, 175–194. https://doi.org/10.7212/karaelmasfen.1591188

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (58)

  1. Ahmad, N., Lin, C., Lau, AKH., Kim, J., Zhang, T., Yu, F., … Lao, XQ. 2024. Estimation of ground-level NO2 and its spatiotemporal variations in China using GEMS measurements and a nested machine learning model. Atmospheric Chemistry and Physics, 24(16), 9645-9665. https://doi.org/10.5194/ACP-24-9645-2024
  2. Becerra-Rondón, A., Ducati, J., Haag, R. 2023. Satellite-based estimation of NO2 concentrations using a machine-learning model: A case study on Rio Grande do Sul, Brazil. Atmósfera, 37, 175-190. https://doi.org/10.20937/ATM.53116
  3. Breiman, L. 2001. Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  4. Castro, A., Künzli, N., Götschi, T. 2017. Health benefits of a reduction of PM10 and NO2 exposure after implementing a clean air plan in the Agglomeration Lausanne-Morges. International Journal of Hygiene and Environmental Health, 220(5), 829-839. https://doi.org/10.1016/J.IJHEH.2017.03.012
  5. Chen, ZY., Zhang, R., Zhang, TH., Ou, CQ., Guo, Y. 2019. A kriging-calibrated machine learning method for estimating daily ground-level NO2 in mainland China. Science of The Total Environment, 690, 556-564. https://doi.org/10.1016/J.SCITOTENV.2019.06.349
  6. Chi, Y., Fan, M., Zhao, C., Yang, Y., Fan, H., Yang, X., … Tao, J. 2022. Machine learning-based estimation of ground-level NO2 concentrations over China. Science of The Total Environment, 807, 150721. https://doi.org/10.1016/J.SCITOTENV.2021.150721
  7. Cichowicz, R., Bochenek, AD. 2024. Assessing the effects of urban heat islands and air pollution on human quality of life. Anthropocene, 46, 100433. https://doi.org/10.1016/J.ANCENE.2024.100433
  8. Cooper, MJ., Martin, RV., Hammer, MS., Levelt, PF., Veefkind, P., Lamsal, LN., … McLinden, CA. 2022. Global fine-scale changes in ambient NO2 during COVID-19 lockdowns. Nature, 601, 380-387. https://doi.org/10.1038/s41586-021-04229-0
  9. Copernicus. 2024. Sentinel-5P NO₂ Data Product. https://sentinels.copernicus.eu/web/sentinel/data-products/-/asset_publisher/fp37fc19FN8F/content/sentinel-5-precursor-level-2-nitrogen-dioxide.
  10. de la Cruz Libardi, A., Masselot, P., Schneider, R., Nightingale, E., Milojevic, A., Vanoli, J., … Gasparrini, A. 2024. High resolution mapping of nitrogen dioxide and particulate matter in Great Britain (2003–2021) with multi-stage data reconstruction and ensemble machine learning methods. Atmospheric Pollution Research, 15(11), 102284. https://doi.org/10.1016/J.APR.2024.102284
  11. Deng, F., Chen, Y., Liu, W., Li, L., Chen, X., Tiwari, P., Qin, K. 2024. Satellite-Based Estimation of Near-Surface NO2 Concentration in Cloudy and Rainy Areas. Remote Sensing, 16(10), 1785. https://doi.org/10.3390/RS16101785
  12. Dokuz, Y., Bozdağ, A., Gökçek, ÖB. 2020. Hava kalitesi parametrelerinin tahmini ve mekansal dağılımı için makine öğrenmesi yöntemlerinin kullanılması. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 9(1), 37-47. https://doi.org/10.28948/NGUMUH.654092
  13. Elbir, T., Kara, M., Bayram, A., Altiok, H., Dumanoglu, Y. 2011. Comparison of predicted and observed PM10 concentrations in several urban street canyons. Air Quality, Atmosphere and Health, 4, 121-131. https://doi.org/10.1007/S11869-010-0080-9
  14. Elbir, T., Muezzinoglu, A. 2004. Estimation of emission strengths of primary air pollutants in the city of Izmir, Turkey. Atmospheric Environment, 38(13), 1851-1857. https://doi.org/10.1016/J.ATMOSENV.2004.01.015
  15. Fu, J., Tang, D., Grieneisen, ML., Yang, F., Yang, J., Wu, G., … Zhan, Y. 2023. A machine learning-based approach for fusing measurements from standard sites, low-cost sensors, and satellite retrievals: Application to NO2 pollution hotspot identification. Atmospheric Environment, 302, 119756. https://doi.org/10.1016/J.ATMOSENV.2023.119756
  16. Ghahremanloo, M., Lops, Y., Choi, Y., Yeganeh, B. 2021. Deep Learning Estimation of Daily Ground-Level NO2 Concentrations From Remote Sensing Data. Journal of Geophysical Research: Atmospheres, 126(21), e2021JD034925. https://doi.org/10.1029/2021JD034925
  17. Goldberg, DL., Anenberg, SC., Griffin, D., McLinden, CA., Lu, Z., Streets, DG. 2020. Disentangling the Impact of the COVID-19 Lockdowns on Urban NO2 From Natural Variability. Geophysical Research Letters, 47(17), e2020GL089269. https://doi.org/10.1029/2020GL089269
  18. Google Earth Engine. 2024. Earth Engine Data Catalog - Sentinel-5P OFFL NO2: Offline Nitrogen Dioxide. https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S5P_OFFL_L3_NO2#description.
  19. Griffin, D., Zhao, X., McLinden, CA., Boersma, F., Bourassa, A., Dammers, E., … Wolde, M. 2019. High-Resolution Mapping of Nitrogen Dioxide With TROPOMI: First Results and Validation Over the Canadian Oil Sands. Geophysical Research Letters, 46(2), 1049-1060. https://doi.org/10.1029/2018GL081095
  20. Grzybowski, PT., Markowicz, KM., Musiał, JP. 2023. Estimations of the Ground-Level NO2 Concentrations Based on the Sentinel-5P NO2 Tropospheric Column Number Density Product. Remote Sensing 2023, Vol. 15, Page 378, 15(2), 378. https://doi.org/10.3390/RS15020378
  21. Gui, K., Che, H., Zeng, Z., Wang, Y., Zhai, S., Wang, Z., … Zhang, X. 2020. Construction of a virtual PM2.5 observation network in China based on high-density surface meteorological observations using the Extreme Gradient Boosting model. Environment International, 141, 105801. https://doi.org/10.1016/J.ENVINT.2020.105801
  22. Gündoğdu, S., Elbir, T. 2024a. A data-driven approach for PM2.5 estimation in a metropolis: random forest modeling based on ERA5 reanalysis data. Environmental Research Communications, 6(3), 035029. https://doi.org/10.1088/2515-7620/AD352D
  23. Gündoğdu, S., Elbir, T. 2024b. Elevating hourly PM2.5 forecasting in Istanbul, Türkiye: Leveraging ERA5 reanalysis and genetic algorithms in a comparative machine learning model analysis. Chemosphere, 364, 143096. https://doi.org/10.1016/J.CHEMOSPHERE.2024.143096
  24. Gündoğdu, S., Tuna Tuygun, G., Li, Z., Wei, J., Elbir, T. 2022. Estimating daily PM2.5 concentrations using an extreme gradient boosting model based on VIIRS aerosol products over southeastern Europe. Air Quality, Atmosphere and Health, 15(12), 2185-2198. https://doi.org/10.1007/S11869-022-01245-5
  25. Hanif, A., Sun, M., Wang, T., Shang, S., Tsang, DCW., Shang, J. 2021. Ambient NO2 adsorption removal by Mg–Al layered double hydroxides and derived mixed metal oxides. Journal of Cleaner Production, 313, 127956. https://doi.org/10.1016/J.JCLEPRO.2021.127956
  26. Hashim, BM., Al-Naseri, SK., Al-Maliki, A., Al-Ansari, N. 2021. Impact of COVID-19 lockdown on NO2, O3, PM2.5 and PM10 concentrations and assessing air quality changes in Baghdad, Iraq. Science of The Total Environment, 754, 141978. https://doi.org/10.1016/J.SCITOTENV.2020.141978
  27. Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., … Thépaut, JN. 2023. ERA5 hourly data on single levels from 1940 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS).
  28. Hu, M., Bai, K., Li, K., Zheng, Z., Sun, Y., Shao, L., … Liu, C. 2024. Improving machine-learned surface NO2 concentration mapping models with domain knowledge from data science perspective. Atmospheric Environment, 322, 120372. https://doi.org/10.1016/J.ATMOSENV.2024.120372
  29. Ibrahim, S., Landa, M., Pešek, O., Brodský, L., Halounová, L. 2022. Machine Learning-Based Approach Using Open Data to Estimate PM2.5 over Europe. Remote Sensing 2022, Vol. 14, Page 3392, 14(14), 3392. https://doi.org/10.3390/RS14143392
  30. Ialongo, I., Virta, H., Eskes, H., Hovila, J., Douros, J. 2020. Comparison of TROPOMI/Sentinel-5 Precursor NO2 observations with ground-based measurements in Helsinki. Atmospheric Measurement Techniques, 13(1), 205-218. https://doi.org/10.5194/AMT-13-205-2020
  31. Kang, Y., Choi, H., Im, J., Park, S., Shin, M., Song, CK., Kim, S. 2021. Estimation of surface-level NO2 and O3 concentrations using TROPOMI data and machine learning over East Asia. Environmental Pollution, 288, 117711. https://doi.org/10.1016/J.ENVPOL.2021.117711
  32. Kharol, SK., McLinden, CA., Sioris, CE., Shephard, MM., Fioletov, V., Van Donkelaar, A., … Martin, RV. 2017. OMI satellite observations of decadal changes in ground-level sulfur dioxide over North America. Atmospheric Chemistry and Physics, 17(9), 5921-5929. https://doi.org/10.5194/ACP-17-5921-2017
  33. Kim, M., Brunner, D., Kuhlmann, G. 2021. Importance of satellite observations for high-resolution mapping of near-surface NO2 by machine learning. Remote Sensing of Environment, 264, 112573. https://doi.org/10.1016/J.RSE.2021.112573
  34. Levelt, PF., Van Den Oord, GHJ., Dobber, MR., Mälkki, A., Visser, H., De Vries, J., … Saari, H. 2006. The ozone monitoring instrument. IEEE Transactions on Geoscience and Remote Sensing, 44(5), 1093-1100. https://doi.org/10.1109/TGRS.2006.872333
  35. Li, M., Wu, Y., Bao, Y., Liu, B., Petropoulos, GP. 2022. Near-Surface NO2 Concentration Estimation by Random Forest Modeling and Sentinel-5P and Ancillary Data. Remote Sensing 2022, Vol. 14, Page 3612, 14(15), 3612. https://doi.org/10.3390/RS14153612
  36. Liu, Y., Chen, X., Huang, S., Tian, L., Lu, Y., Mei, Y., … Xiang, H. 2015. Association between Air Pollutants and Cardiovascular Disease Mortality in Wuhan, China. International Journal of Environmental Research and Public Health 2015, Vol. 12, Pages 3506-3516, 12(4), 3506-3516. https://doi.org/10.3390/IJERPH120403506
  37. Long, S., Wei, X., Zhang, F., Zhang, R., Xu, J., Wu, K., … Li, W. 2022. Estimating daily ground-level NO2 concentrations over China based on TROPOMI observations and machine learning approach. Atmospheric Environment, 289, 119310. https://doi.org/10.1016/J.ATMOSENV.2022.119310
  38. Muñoz Sabater, J. 2019. ERA5-Land hourly data from 1950 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS).
  39. Ngo, TX., Phan, HDT., Nguyen, TTN. 2023. Development of ground-level NO2 models in Vietnam using machine learning and satellite observations with ancillary data. Frontiers in Environmental Science, 11, 1187592. https://doi.org/10.3389/FENVS.2023.1187592
  40. Qin, K., Han, X., Li, D., Xu, J., Li, D., Loyola, D., … Yuan, L. 2020. Satellite-based estimation of surface NO2 concentrations over east-central China: A comparison of POMINO and OMNO2d data. Atmospheric Environment, 224, 117322. https://doi.org/10.1016/J.ATMOSENV.2020.117322
  41. Schneider, R., Vicedo-Cabrera, AM., Sera, F., Masselot, P., Stafoggia, M., de Hoogh, K., … Gasparrini, A. 2020. A Satellite-Based Spatio-Temporal Machine Learning Model to Reconstruct Daily PM2.5 Concentrations across Great Britain. Remote Sensing 2020, Vol. 12, Page 3803, 12(22), 3803. https://doi.org/10.3390/RS12223803
  42. Shao, Y., Zhao, W., Liu, R., Yang, J., Liu, M., Fang, W., … Ma, Z. 2023. Estimation of daily NO2 with explainable machine learning model in China, 2007–2020. Atmospheric Environment, 314, 120111. https://doi.org/10.1016/J.ATMOSENV.2023.120111
  43. Shetty, S., Schneider, P., Stebel, K., David Hamer, P., Kylling, A., Koren Berntsen, T. 2024. Estimating surface NO2 concentrations over Europe using Sentinel-5P TROPOMI observations and Machine Learning. Remote Sensing of Environment, 312, 114321. https://doi.org/10.1016/J.RSE.2024.114321
  44. Sünsüli, M., Kalkan, K. 2022. Sentinel-5p Uydu Görüntüleri İle Azot Dioksit (NO2) Kirliliğinin İzlenmesi. Türkiye Uzaktan Algılama Dergisi, 4(1), 1-6. https://doi.org/10.51489/TUZAL.1056261
  45. Tao, C., Jia, M., Wang, G., Zhang, Y., Zhang, Q., Wang, X., … Wang, W. 2024. Time-sensitive prediction of NO2 concentration in China using an ensemble machine learning model from multi-source data. Journal of Environmental Sciences, 137, 30-40. https://doi.org/10.1016/J.JES.2023.02.026
  46. Tuna Tuygun, G., Elbir, T. 2023. Estimation of particulate matter concentrations in Türkiye using a random forest model based on satellite AOD retrievals. Stochastic Environmental Research and Risk Assessment, 37(9), 3469-3491. https://doi.org/10.1007/s00477-023-02459-4
  47. Tuna Tuygun, G., Gündoğdu, S., Elbir, T. 2021. Estimation of ground-level particulate matter concentrations based on synergistic use of MODIS, MERRA-2 and AERONET AODs over a coastal site in the Eastern Mediterranean. Atmospheric Environment, 261, 118562. https://doi.org/10.1016/J.ATMOSENV.2021.118562
  48. Ünal Çilek, M. 2022. Troposferik Nitrojen Dioksitin (NO2) COVID-19 Pandemisinde Mekânsal ve Zamansal Analizi: Adana-Mersin Bölgesi. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 27(3), 581s-594. https://doi.org/10.53433/YYUFBED.1119418
  49. Ünaldı, S., Yalçın, N. 2022. Hava Kirliliğinin Makine Öğrenmesi Tabanlı Tahmini: Başakşehir Örneği. Mühendislik Bilimleri ve Araştırmaları Dergisi, 4(1), 35-44. https://doi.org/10.46387/BJESR.1055946
  50. Veefkind, JP., Aben, I., McMullan, K., Förster, H., de Vries, J., Otter, G., … Levelt, PF. 2012. TROPOMI on the ESA Sentinel-5 Precursor: A GMES mission for global observations of the atmospheric composition for climate, air quality and ozone layer applications. Remote Sensing of Environment, 120, 70-83. https://doi.org/10.1016/J.RSE.2011.09.027
  51. Wei, J., Li, Z., Sun, L., Xue, W., Ma, Z., Liu, L., … Cribb, M. 2022. Extending the EOS Long-Term PM2.5Data Records since 2013 in China: Application to the VIIRS Deep Blue Aerosol Products. IEEE Transactions on Geoscience and Remote Sensing, 60. https://doi.org/10.1109/TGRS.2021.3050999
  52. Weinmayr, G., Romeo, E., de Sario, M., Weiland, SK., Forastiere, F. 2010. Short-Term effects of PM10 and NO2 on respiratory health among children with asthma or asthma-like symptoms: A systematic review and Meta-Analysis. Environmental Health Perspectives, 118(4), 449-457. https://doi.org/10.1289/ehp.0900844
  53. Yao, F., Si, M., Li, W., Wu, J. 2018. A multidimensional comparison between MODIS and VIIRS AOD in estimating ground-level PM2.5 concentrations over a heavily polluted region in China. Science of The Total Environment, 618, 819-828. https://doi.org/10.1016/J.SCITOTENV.2017.08.209
  54. Yavaşlı, DD., Ölgen, MK. 2022. Impacts of COVID-19 Pandemic on Tropospheric NO2 over Turkey. Aegean Geographical Journal, 31(2), 255-264. https://doi.org/10.51800/ECD.1109104
  55. Zhang, Q., Pan, Y., He, Y., Walters, WW., Ni, Q., Liu, X., … Jiang, C. 2021. Substantial nitrogen oxides emission reduction from China due to COVID-19 and its impact on surface ozone and aerosol pollution. Science of The Total Environment, 753, 142238. https://doi.org/10.1016/J.SCITOTENV.2020.142238
  56. Zhang, R., Zhang, Y., Lin, H., Feng, X., Fu, TM., Wang, Y. 2020. NOx Emission Reduction and Recovery during COVID-19 in East China. Atmosphere 2020, Vol. 11, Page 433, 11(4), 433. https://doi.org/10.3390/ATMOS11040433
  57. Zhao, Z., Lu, Y., Zhan, Y., Cheng, Y., Yang, F., Brook, JR., He, K. 2023. Long-term spatiotemporal variations in surface NO2 for Beijing reconstructed from surface data and satellite retrievals. Science of The Total Environment, 904, 166693. https://doi.org/10.1016/J.SCITOTENV.2023.166693
  58. Zhu, F., Ding, R., Lei, R., Cheng, H., Liu, J., Shen, C., … Cao, J. 2019. The short-term effects of air pollution on respiratory diseases and lung cancer mortality in Hefei: A time-series analysis. Respiratory Medicine, 146, 57-65. https://doi.org/10.1016/J.RMED.2018.11.019