1887
PDF

Abstract

Summary

An analysis of vertical surface displacements above the metro between the “Demiivska” and “Lybidska” stations in Kyiv was conducted, where tunnel lining deformations were detected in December 2023. Five vertical displacement maps were obtained using the D-InSAR method for the period from March 2022 to December 2023. Anomalous zones (maximum deviations compared to background values) were identified, and surface dynamics were tracked across five observation periods. The Gaussian Process Regression method was applied to analyze displacement data. A predictive mathematical model was developed in Python based on a custom algorithm.

For the first time, predicted vertical displacement values were determined for the area above the metro track. The obtained predictions closely align in magnitude with the average observed values. The greatest discrepancies between predicted and observed values indicate that factors influencing the underground tunnel deformation are present both directly above it and in its immediate vicinity. The reliability of the developed model may be affected by uncertainties such as the rapid commencement of repair works or water supply network failures. Therefore, the model requires consideration of both anthropogenic and natural factors, including changes in engineering-geological conditions.

The Gaussian Process Regression method is suitable for predicting vertical surface displacements at the object level and can be utilized in other areas with underground infrastructure for hazard prediction and early warning of emergencies.

EAGE Publications BV © 2025 The Authors © European Association of Geoscientists and Engineers
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.2025510054
2025-04-14
2026-02-19

  • From This Site

    /content/papers/10.3997/2214-4609.2025510054
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/2214-4609/2025/monitoring_2025/Mon25-054.html?itemId=/content/papers/10.3997/2214-4609.2025510054&mimeType=html&fmt=ahah

References

  1. Bishop, C. M. (2006). Pattern Recognition and Machine Learning (Information Science and Statistics). In Springer eBooks. https://dl.acm.org/citation.cfm?id=l 162264.
     [Google Scholar]
  2. Heinrich, S., & Kiefer, B. (2016). Spatio-Temporal Gaussian Processes for Remote Sensing. Remote Sensing, 8(11), 925.
     [Google Scholar]
  3. Hudak, V., Cherevko, I., Zatserkovny, V., Nikolaienko, O., & Lazorenko-Hevel, N. (2021). Geoinformation modeling of exogenous geological processes on the territory of the Kyiv-Pechersk Lavra. Geoinformatics, 2021. https://doi.org/10.3997/2214-4609.20215521048
     [Google Scholar]
  4. Kril, T. (2017). Causes of some hazardous engineeringgeological processes on urban territories. E3S Web of Conferences, 24, 01009. https://doi.org/10.1051/e3sconf/20172401009
     [Google Scholar]
  5. Kril, T., & Orlenko, T. (2022). Surface dynamics assessment as a landslide hazard factor by remote sensing data. 16th International Conference Monitoring of Geological Processes and Ecological Condition of the Environment, 1–5. https://doi.org/10.3997/2214-4609.2022580246
     [Google Scholar]
  6. LiZ., WangY., MuJ., LiaoW., & ZhangK. (2021). InSAR Deformation Time-series Reconstruction for Rainfall-induced Landslides Based on Gaussian Process Regression. 13th Inter. Conference on Machine Learning and Computing. 117–126. https://doi.org/10.1145/3457682.3457700
     [Google Scholar]
  7. Minh, D. H. T., Hanssen, R., & Rocca, F. (2020). Radar Interferometry: 20 years of development in time series techniques and future Perspectives. Remote Sensing, 12(9), 1364. https://doi.org/10.3390/rs12091364
     [Google Scholar]
  8. Pepe, A., & Calo, F. (2017). A review of Interferometric Synthetic Aperture RADAR (INSAR) Multi-Track approaches for the retrieval of Earth's surface displacements. Applied Sciences, 7(12), 1264. https://doi.org/10.3390/app7121264
     [Google Scholar]
  9. Piestova, I. O., Stankevich, S. A., & Kostolny, J. (2017). Multispectral imagery super-resolution with logical reallocation of spectra. 2017 International Conference on Information and Digital Technologies (IDT), 322–326. https://doi.org/10.1109/dt.2017.8024316
     [Google Scholar]
  10. Rasmussen, C. E., & Williams, C. K. I. (2005). Gaussian processes for machine learning. https://doi.org/10.7551/mitpress/3206.001.0001
     [Google Scholar]
  11. Serco Italia SPA. (2018). Land subsidence with Sentinel-1 using SNAP (Version 1.2). Retrieved from https://rus-copernicus.eu/portal/the-rus-library/learn-bv-vourself
     [Google Scholar]
  12. Vyzhva, Z. O. (2019). Statistical modeling in geology (Electronic edition, 395 p.). Retrieved from https://mechmat.knu.Ua/wp-content/uploads/2020/11/posibnvk-vyzhva.z.o.2doc.pdf
     [Google Scholar]
/content/papers/10.3997/2214-4609.2025510054
Loading
Gaussian Process Regression for D-InSAR Analysis of Vertical Surface Displacements above Underground Structures
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.2025510054
/content/papers/10.3997/2214-4609.2025510054
/content/papers/10.3997/2214-4609.2025510054
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