Empress Catherine II Saint-Petersburg Mining University, Saint-Petersburg, Russia

N. A. Danileva, Associate Professor, Candidate of Geological and Mineralogical Sciences, Danileva_na@pers.spmi.ru

In this article, a method for recovering acoustic logging data is considered as a casestudy of a potassium–magnesium salt deposit in the Kaliningrad Region. The main task set in the framework of the study is to determine the possibility of recovering the interval travel time of elastic waves (acoustic logging) in structurally complex geological section with contrast elastic properties. The limited range of well log surveys dictates the need to synthesize interval travel time curves in wells yet uncovered by acoustic logging due to their “age”. The synthesized interval travel time curves can further clarify geological structure of the above-salt interlaid carbonate and hydrochemical strata, validate location of the impermeable stratum and enable comparison of the well logging data with ground-based seismic exploration results. The available well logging data allowed substantiating the applicability of N. Z. Zalyaev’s model based on the relationship between the interval travel time and neutron logging carried out in most wells of the test deposit. The coefficient of determination between the synthesized data and the initial acoustic logging curves over the entire study interval is 0.778, which seems to be sufficient for its use. However, within the framework of the study, it is proposed to supplement the method of calculating the acoustic logging curve with the lithology data using “stratum-by-stratum modification” and selecting normalization coefficients to the equations per each type of rock. The applied modification of the acoustic logging curve calculation with regard to the lithology of the section has the best coefficient of determination of 0.913. The Russian Gintel software package developed at GIFTS LLC is used to implement the calculations.

1. Zubov V. P., Smychnik A. D. The concept of reducing the risks of potash mines flooding caused by groundwater inrush into excavations. Journal of Mining Institute. 2015.
Vol. 215. pp. 29–37.2. Sirenko Yu. G., Kovalsky E. R. Improvement of selective potash extraction using shortwall mining with partial backfill. Gornyi Zhurnal. 2016. No. 1. pp. 24–26.
3. Frid A., Frid V. Moisture efect on asphalt dielectric permittivity: simulating, sensitivity analysis and experimental validation. International Journal of Pavement Research and Technology. 2024. Vol. 17, Iss. 4. pp. 999–1013.
4. Zhao H., Yang T., Ni Y.-D., Liu X.-G., Xu Y.-P. et al. Reconstruction method of irregular seismic data with adaptive thresholds based on different sparse transform bases. Applied Geophysics. 2021. Vol. 18, Iss. 3. pp. 345–360.
5. Kumar R., Kumar R., Bhardwaj A., Singh A., Singh Sh. et al. Multivariate statistical analysis and geospatial approach for evaluating hydro-geochemical characteristics of meltwater from Shaune Garang glacier, Himachal Pradesh, India. Acta Geophysica. 2023. Vol. 71, Iss. 1. pp. 323–339.
6. Vakhitova G. R., Lystseva T. S. Forecasting of interval time in sonic logging with a limited input information. Karotazhnik. 2014. No. 9(243). pp. 4–14.
7. Vakhitova G. R., Lystseva T. S., Polyudova N. Yu., Sakhautdinov I. R. Restoration of acoustic properties of reservoir using the logging data. Proceedings of the 12^th Conference and Exhibition Engineering Geophysics 2016. Anapa, 2016. pp. 297–301.
8. Danileva N. A., Danilev S. M., Bolshakova N. V. Allocation of a deep-lying brine aquifer in the rocks of a chemogenic section based on the data of geophysical well logging and 2D seismic exploration. Journal of Mining Institute. 2021. Vol. 250. pp. 501–511.
9. Kindyuk V. A., Sobolev A. Yu. Prediction of Young’s modulus from geophysical logs using neural networks. Interekspo Geo-Sibir. 2013. Vol. 2, No. 2. pp. 192–196.
10. Kulikov V. V. Calculation procedures of synthesized sound and density logging curves in application at mineral deposits in the Samara Region : Review. Petrophysical Modeling of Sedimentary Strata : II Baltic Workshop. Petergof, 2013.
11. Zaripova E. A., Enikeev M. R. Recovery of logging curves using machine learning methods. Mathematical Modeling, Numerical Methods and Software Systems : Proceedings of IX Voskresensky International Youth Workshop. Saransk : SVMO, 2020. pp. 62–65.
12. Paklin N. B., Mukhamadiev R. S. Application of learning algorithms in interpretation of GIS data. Burenie i neft. 2005. No. 5. pp. 38–40.
13. Ashkar G. Kh. Application of machine learning in synthesis of GIS data. Inzhenernaya praktika. 2022. No. 8. pp. 26–32.
14. Berseneva S. A., Vakhitova G. R., Polyudova N. Yu. Prediction of rock density distribution according to neutron log. Readings of A. I. Bulatov : Materials of I International Conference. Krasnodar : Yug, 2017. Vol. 1. pp. 36–38.
15. Khayrullin A. R., Vakhitova G. R. Restoration of the petroelastic properties of rocks according to well log data. Bulatov’s Lectures : Proceedings of III International Conference. Krasnodar : Yug, 2019. Vol. 1. pp. 151–155.
16. Schaul T., Bayer J., Wierstra D., Sun Y., Felder M. et al. PyBrain. Journal of Machine Learning Research. 2010. Vol. 11. pp. 743–746.
17. Aristodemou E., Pain C., De Oliveira C., Goddard T., Harris C. Inversion of nuclear welllogging data using neural networks. Geophysical Prospecting. 2005. Vol. 53, Iss. 1. pp. 103–120.
18. Pushpa P. M. M. R., Manimala K. Implementation of hyperbolic tangent activation function in VLSI. International Journal of Advanced Research in Computer Science & Technology. 2014. Vol. 2, Issue Special 1. pp. 225–228.
19. Chhun K. T., Woo S. I., Yune C.-Y. Inversion of 2D cross-hole electrical resistivity tomography data using artificial neural network. Science Progress. 2022. Vol. 105, Iss. 1. DOI: 10.1177/00368504221075465
20. Zalyaev N. Z. Procedure of Automated Interpretation of Well Logging Data. Minsk : Universitetskoe, 1990. 144 p.
21. Turenko S. K., Cherepanov E. A. Using the data of neutron logging for constructing seismic and geological models of oil and gas in Western Siberia objects. Izvestiya vuzov. Neft i gaz. 2016. No. 2(116). pp. 27–32.
22. Lavrenkova N. V., Nekrasova T. V., Toropov A. S. Petrophysical framework for seismic inversion—Data preparation and elastic property modeling. Petrophysical Modeling of Sedimentary Rocks : I Baltic Workshop. Petergof, 2012.
23. Denisov V. S. Features of data recovery in the carbonate section using the layer-by-layer analysis technology. Bulatov’s Lecturers : Proceedings of VI International Conference. Krasnodar : Yug, 2022. Vol. 1. pp. 54–60.
24. Ngoie S., Lunda J.-M., Mbuyu A., Kabulo J.-F. Application of synthetic observations to develop an artificial neural network for mine dewatering. International Research Journal of Engineering and Technology. 2017. Vol. 4, Iss. 12. pp. 923–927.
25. Enikeev B. N., Okhrimenko A. B., Smirnov O. A. Functional (fundamental) and statistical interrelations in petrophysics (problems of comparison among similar petrophysical interrelations). Karotazhnik. 2011. No. 7(205). pp. 102–117.