1887
PDF

Abstract

Summary

The PyLEnM framework based on unsupervised machine learning (ML) algorithms was applied to analyse Chernobyl groundwater monitoring data set comprising of 74 monitoring wells within the 10-km zone of Chernobyl nuclear power plant for the period from 1990 to 2019. Concentrations of 90Sr and 137Cs in groundwater were studied depending on the groundwater water level, surface deposition of fallout radionuclides, monitoring borehole design characteristics and distance from the source of release. No strong positive correlation of radionuclide groundwater concentrations with land surface contamination was determined, suggesting that a larger set of attributes is needed to explain variability of groundwater data. Time trends of 90Sr in groundwater and results of ML analyses are consistent with the conceptual model assuming a gradual release from dissolving fuel particles and its downward transport through vadose zone to groundwater. The results for 137Cs can likely be explained by a combination of facilitated transport and fixation to clay minerals in the topsoil layer. The conducted pilot computational analysis of the Chernobyl dataset offers further opportunities for in-depth research on the application of AI/ML-guided analyses in order to improve conceptual understanding of radionuclide migration process and draw lessons from radiation monitoring experience.

EAGE Publications BV © 2023 The Authors © European Association of Geoscientists and Engineers
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.2023520157
2023-11-07
2026-02-14

  • From This Site

    /content/papers/10.3997/2214-4609.2023520157
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/2214-4609/2023/monitoring'2023/Mon23-157.html?itemId=/content/papers/10.3997/2214-4609.2023520157&mimeType=html&fmt=ahah

References

  1. Bugai, D., Kireev, S., Hoque, M. A., Kubko, Y., Smith, J. (2022). Natural attenuation processes control groundwater contamination in the Chernobyl exclusion zone: evidence from 35 years of radiological monitoring.Sci. Reports, 2022. 12:18215. https://doi.org/10.1038/s41598-022-22842-5
     [Google Scholar]
  2. Bugai, D., Smith, J., Hoque, M.A. (2020). Solid-liquid distribution coefficients (Kd-s) of geological deposits at the Chernobyl Nuclear Power Plant site with respect to Sr, Cs and Pu radionuclides: A short review.Chemosphere, 242, 125175. https://doi.org/10.1016/J.CHEMOSPHERE.2019.125175
     [Google Scholar]
  3. Cheng, T., Saiers, J.E. (2015) Effects of dissolved organic matter on the co-transport of mineral colloids and sorptive contaminants, J. Contam. Hydrol., 177, 148–157. https://doi.org/10.1016/j.jconhyd.2015.04.005
     [Google Scholar]
  4. Haggerty, R., Sun, J., Yu, H., Li, Y. (2023) Application of machine learning in groundwater quality modeling - A comprehensive review.Water Res., 233, 119745. https://doi.org/10.1016/j.watres.2023.119745
     [Google Scholar]
  5. Kashparov, V.A., Lundin, S.M., Zvarich, S.I., Yoschenko, V.I., Levtchuk, S.E., Khomutinin, YuV., Maloshtan, I.N., Protsak, V.P. (2003). Territory contamination with the radionuclides representing the fuel component of Chernobyl fallout.Sci. Total Environ, 317 (1–3), 105–119.
     [Google Scholar]
  6. Meray, A., Sturla, S., Siddiquee, M., Serata, R., Uhlemann, S., Gonzalez-Raymat, H., Denham, M., Upadhyay, H., Lagos, L., Eddy-Dilek, C., Wainwright, H. (2022). PyLEnM: A Machine Learning Framework for Long-Term Groundwater Contamination Monitoring Strategies.Environ. Sci. Technol., 56, 5973–5983. https://doi.org/10.1021/acs.est.1c07440
     [Google Scholar]
  7. Rastorguev, I., Rastorguev, A. (2022). Calculated 137Cs Ingress into Groundwater via the Aeration Zone at the Demenka Test Site as a Result of the Accident at the Chernobyl Nuclear Power Plant.Atomic Energy, 131, 298–302. https://doi.org/10.1007/s10512-022-00882-4
     [Google Scholar]
  8. Shestopalov, V., Bublias, V.N., Bohuslavsky, A.S., Bixio, A.C., Putti, M. (2015). Modeling of radionuclide fast migration paths at a typical depression in the Chernobyl exclusion zone. In: Groundwater 2000.Proceedings of the Int. Conf. on Groundwater Research, Copenhagen, Denmark, 6–8 June 2000 (Eds P. L.Bjerg, P.Engesgaard, T.D.Krom), CRC Press, London. https://doi.org/10.1201/9781003078593-65
     [Google Scholar]
/content/papers/10.3997/2214-4609.2023520157
Loading
Machine Learning Analysis Using Pylenm Package of Chernobyl Long-Term Groundwater Monitoring Data: First Experience and Opportunities
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.2023520157
/content/papers/10.3997/2214-4609.2023520157
/content/papers/10.3997/2214-4609.2023520157
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error