Analysis of the influence of natural and anthropogenic factors on radon flux density in Moscow using machine learning methods

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

During routine measurements of radon flux density for construction purposes in Moscow, the areas were found with abnormally high radon flux densities exceeding 400 mBq m–2 s–1. These values far exceed those average values around 24–40 mBq m–2 s–1 for local sandy and clay soils, which is compounded with the fact that the area under study doesn’t contain any active faults or natural soils rich in uranium. Therefore, the question arises, whether these high values are of technogenic or natural origin. This paper uses machine learning algorithms to find the answer to these questions. Machine learning algorithms including random forest trees and artificial neural networks were used to try and predict radon flux density anomalies on a city scale. Predictors used included maps of geodynamically active areas, lineaments, distances to heavy rail infrastructure such as metro tunnels and surface-level rail. Additionally, normal predictors of radon such as 226Ra concentration in soil, quaternary soil type and elevation were used for the predictions. Predictions were made for both anomaly-free and anomaly included datasets. Training data included radon flux data for Moscow with both anomalous and background values which included 931 data points, of which 112 was classified as anomalous (more than 400 mBq m–2 s–1). Based on the predictions obtained, factors which influence radon flux density and those that may produce anomalous values were underlined.

Full Text

Restricted Access

About the authors

S. G. Gavriliev

Sergeev Institute of Environmental Geoscience, Russian Academy of Sciences

Email: tbp111@inbox.ru
Russian Federation, Ulanskii per. 13, bld.2, Moscow, 101000

T. B. Petrova

Lomonosov Moscow State University

Author for correspondence.
Email: tbp111@inbox.ru

Department of Radiochemistry, Faculty of Chemistry

Russian Federation, Leninskie Gory 1, Moscow, 119991

P. S. Miklyaev

Sergeev Institute of Environmental Geoscience, Russian Academy of Sciences

Email: peterm7@inbox.ru
Russian Federation, Ulanskii per. 13, bld.2, Moscow, 101000

E. A. Karfidova

Sergeev Institute of Environmental Geoscience, Russian Academy of Sciences

Email: tbp111@inbox.ru
Russian Federation, Ulanskii per. 13, bld.2, Moscow, 101000

References

  1. Makarov, V.I., Dorozhko, A.L., Makarova, N.V., Makeev, V.M. [Modern geodynamically active zones of platforms.] Geoekologiya, 2007, no. 2, pp. 99–110. (in Russian)
  2. Makarova, N.V., Makeev, V.I., Dorozhko, A.L., Sukhanova, T.V., Korobova, I.V. [Geodynamic systems and geodynamically active zones of the East-European platform]. Byulleten MOIP, ser. Geol, 2016, vol. 91, pp. 4–5. (in Russian)
  3. Marennyy, A.M., Tsapalov, A.A., Miklyaev, P.S., Petrova T.B. [Regularities in radon field formation in geoenvironment]. Moscow, Pero Publ., 2016, 394 p. (in Russian)
  4. Miklyaev, P.S., Makarov, V.I., Dorozhko, A.L., Petrova, T.B., Marennyi, M.A., Marennyi, A.M., Makeev V.M. [Radon field of Moscow]. Geoekologiya, 2013, no. 2, pp. 172–187. (in Russian)
  5. Osipov, V.I. [Large-scale geological mapping of Moscow territory]. Geoekologiya, 2011, no. 3, pp. 195–197. (in Russian)
  6. Bossew, P., Cinelli, G., Ciotoli, G., Crowley, Q.G., De Cort, M., Elío Medina, J., Gruber, V., Petermann, E., Tollefsen, T. Development of a geogenic radon hazard index—concept, history, experiences. Int. J. Environ. Res. Public Health, 2020, no. 17, p. 4134. https://doi.org/10.3390/ijerph17114134
  7. Di Carlo, C., Maiorana, A., Bochicchio, F. Indoor radon: sources, transport mechanisms and influencing parameters. IntechOpen, 2023. doi: 10.5772/intechopen.111710
  8. Friedman, J. H. Multivariate adaptive regression splines (with discussion). The Annals of Statistics, 1991, no. 19, pp. 1–141.
  9. Gavriliev, S., Petrova, T. , Miklyaev, P. Factors influencing radon transport in the soils of Moscow. Environ. Sci. Pollut. Res., 2022, no. 29, pp. 88606–88617. https://doi.org/10.1007/s11356-022-21919-y
  10. Gavriliev, S., Petrova, T., Miklyaev, P., Karfidova, E. Predicting radon flux density from soil surface using machine learning and GIS data. Science of the Total Environment, 2023, no. 903, p. 166348, https://doi.org/10.1016/j.scitotenv.2023.166348
  11. Radiological protection against radon exposure. ICRP Publication no. 126, 2014. https://www.icrp.org/publication.asp?id=ICRP%20Publication%20126
  12. Janik, M., Bossew, P., Kurihara, O.. Machine learning methods as a tool to analyze incomplete or irregularly sampled radon time series data. Science of the Total Environment, 2018, no. 630, pp.1155–1167.
  13. Mair, J., Petermann, E., Lehné, R., Henk, A. Can neotectonic faults influence soil air radon levels in the Upper Rhine Graben? An exploratory machine learning assessment. Science of the Total Environment, 2024, no. 956, p. 177179, https://doi.org/10.1016/j.scitotenv.2024.177179
  14. Miklyaev, P., Petrova, T., Marennyy, A., Shchitov, D., Sidyakin, P., Murzabekov, M., Lopatin, M. High seasonal variations of the radon exhalation from soil surface in the fault zones (Baikal and North Caucasus regions). Journal of Environmental Radioactivity, 2020, no. 219, pp. 106271.
  15. Miklyaev, P.S., Petrova, T.B., Shchitov, D.V., Sidyakin, P.A., Murzabekov, M.A., Tsebro, D.N., Marennyy, A.M., Nefedov, N.A., Gavriliev, S.G. Radon transport in permeable geological environments. Sci. Total Environ., 2022, vol. 852, p. 158382. doi: 10.1016/j.scitotenv.2022.158382.
  16. Nazaroff, W.W. Radon transport from soil to air. Reviews of Geophysics, 1992. vol. 30, issue 2, pp.137–160. https://doi.org/10.1029/92rg00055
  17. Osipov, V.I., Burova, V.N., Zaikanov, V.G., Molodykh, I.I., Pyrchenko, V.A., Savis’ko, I.S. A map of large-scale (detail) engineering geological zoning of Moscow territory, Water Resources, 2012, no. 39(7), pp. 737–746. doi: 10.1134/S0097807812070093.
  18. Petermann, E., Bossew, P., Kemski, J., Gruber, V., Suhr, N., Hoffmann, B., Development of a high-resolution indoor radon map using a new machine learning- based probabilistic model and German radon survey data. Environ. Health Perspect, 2024, no.132 (9), p. 97009. https://doi.org/10.1289/EHP14171
  19. Petermann, E., Meyer, H., Nussbaum, M., & Bossew, P. Mapping the geogenic radon potential for Germany by machine learning. 2020. https://doi.org/10.5194/egusphere-egu2020-8501
  20. Rezaie, F., Panahi, M., Bateni, S. M., Kim, S., Lee, J., Lee, J., Yoo, J., Kim, H., Won Kim, S., & Lee, S.. Spatial modeling of geogenic indoor radon distribution in Chungcheongnam-do, South Korea using enhanced machine learning algorithms. Environment International, 2023, no. 171, p. 107724. https://doi.org/10.1016/j.envint.2022.107724
  21. Timkova, J., Fojtikova, I., Pacherova, P. Bagged neural network model for prediction of the mean indoor radon concentration in the municipalities in Czech Republic. Journal of Environmental Radioactivity, 2017, no. 166, pp. 398–402. https://doi.org/10.1016/j.jenvrad.2016.07.008
  22. Torkar, D., Zmazek, B., Vaupotič, J., Kobal, I. Application of artificial neural networks in simulating radon levels in soil gas. Chemical Geology, 2010, vol. 270, issues 1–4, pp.1–8. https://doi.org/10.1016/j.chemgeo.2009.09.017
  23. Tsapalov, A., Kovler, K., Miklyaev, P. Open charcoal chamber method for mass measurements of radon exhalation rate from soil surface. Journal of Environmental Radioactivity, 2016, no.160, pp. 28–35. https://doi.org/10.1016/j.jenvrad.2016.04.016
  24. Sources and effects of ionizing radiation. UNSCEAR, 2000, no.1. https://www.unscear.org/unscear/en/publications/2000_1.html. Accessed April 15, 2022 https://doi.org/10.1016/j.jenvrad.2020.106271
  25. WHO Handbook on Indoor Radon: a public health perspective. Hajo Zeeb and Ferid Shannoun, Eds., Geneva, WHO Press, 2009

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Layout of measurement sites in Moscow.

Download (492KB)
Indexing metadata
3. Fig. 2. Maps of primary predictors used for forecasts using machine learning methods (explanations in the text).

Download (876KB)
Indexing metadata
4. Fig. 3. Map of the PPR forecast compiled using: a - background data set and the Random Forest algorithm; b - the full data set (anomalous and background sites). Random Forest algorithm with quantile color scaling. Legend: 1 - sites with PPR anomalies, 2 - thalwegs, 3 - sites with background PPR values, 4 - lineaments, 5 - geodynamically active zones, 6 - slopes greater than 8°, 7 - railways, 8 - metro lines.

Download (975KB)
Indexing metadata

Copyright (c) 2025 Russian academy of sciences