New methodology for Calculating Effective Thickness Maps Using Machine Learning at the Limit of Seismic Survey Resolution
DOI:
https://doi.org/10.17308/geology/1609-0691/2026/1/107-116Keywords:
seismic survey, seismic data interpretation, thin layers, machine learningAbstract
Introduction: the vertical resolution of seismic data is limited to 1/8 to 1/4 of the wavelength. To calculate thickness maps beyond the resolution limits, new interpretation algorithms must be applied.
Methodology: in this paper, the authors propose an algorithm for calculating effective thickness maps beyond the resolution of seismic surveys.
The methodology is based on identifying sedimentary slices and seismic attributes with a high correlation (greater than 0.75) with the effective formation thickness and using these attributes as a training dataset for machine learning algorithms. Among the resulting predictive maps, the one with the smallest root-mean-square error is selected, and areas with the greatest uncertainty in the calculations are analyzed.
Results and discussion: as a result of calculations, maps of effective thicknesses were obtained using various machine learning methods. The quality of the results was assessed using the root-mean-square error calculation. Analysis of the probability maps and the standard deviation map of the implementations allows identifying areas with the greatest uncertainty.
Conclusion: the application of the developed algorithm allows for selecting the optimal method for calculating effective thickness maps beyond the resolution limits of seismic surveys.
Downloads
References
1. Widess M. B. How thin is a thin bed? Geophysics, 1973, vol. 38, pp. 1176–1180
2. Gertner H., Klimmer G. Ob opredelenii razionalnoy plotnosti seismicheskih nabludeniy po velichine zony Frenelya [On determining the rational density of seismic observations based on the size of the Fresnel zone]. I nauchnogo seminara stran-chlenov SJeV po neftjanoj geofizike. T. 1: Sejsmorazvedka: sb. dokladov [Collection of reports of the II scientific seminar of the CMEA member countries on petroleum geophysics], Moscow publ., 1982, no 1, pp. 339−352 (In Russ.)
3. Gogonenkov G. N., Ptecov S. N. Seismorazvedka vysokogo razresheniya [High Resolution Seismic Survey]. Moscow, VNIIOENG publ., 1981. 26 p. (In Russ.)
4. Saeed W., Zhang H., Guo Q., Ali A., Azeem T., Toqeer M., Munawar M., Hussain M. An integrated petrophysical-based wedge modeling and thin bed AVO analysis for improved reservoir characterization of Zhujiang Formation, Huizhou Sub-Basin, China: A case study. Open Geosciences, 2020, vol. 12, pp. 256–274
5. Marfurt K. J., Kirlin R. L. Narrow-band spectral analysis and thin-bed tuning. Geophysics, 2001, vol. 66, no. 4, pp. 1274–1283
6. Charles I. P., Castagna J. P. Layer-thickness determination and stratigraphic interpretation using spectral inversion: Theory and application. Geophysics, 2008, vol. 73, pp. 37–48
7. Bacon M., Simm R., Redshaw T. 3D Seismic interpretation, Cambridge University Press, 2007, 224 р.
8. Baranskii N. L., Inozemtsev A. N., Kolesov S. V., Potapov O. A. Vysokorazreshayushchaya seysmorazvedka – innovatsionnaya tekhnologiya poiskov mestorozhdeniy nefti i gaza [High-resolution seismic survey − an innovative technology for oil and gas exploration]. Pribory i sistemy razvedochnoy geofiziki − Exploratory geophysics instruments and systems, 2004, no. 2, pp. 16–21 (In Russ.)
9. Mougenot D. Marine, seabed, and land seismic equipment for broadband acquisition: A review. Geophysical Prospecting, 2018, vol. 66, no. 5, pp. 922–933.
10. Egan M. S., Seissiger J., Salama A. El-Kaseeh G. The influence of spatial sampling on resolution. CSEG Recorder, 2010, vol. 35, pp. 29–36.
11. Zhou J., Chia P., Li J. Unlocking the full potential of broadband data with advanced processing technology: A case study from NWS Australia. 77th EAGE Conference and Exhibition, 2015, pp. 1–5
12. Wen X., Yang J., Li L. Low-frequency sparse double-constrained broadband seismic impedance inversion. Natural Gas Industry B., 2019, vol. 6, pp. 556–563.
13. Chopra S., Castagna J., Xu Y., Tonn R. Thin-bed reflectivity inversion and seismic interpretation. SEG Technical Program Expanded Abstracts. Society of Exploration Geophysicists, 2007, pp. 1923–1927.
14. Arkhipov A.A. Osnovy sovremennykh metodov rasshireniya spektra seysmicheskoy zapisi. Tekhnologiya «NSEIS» [Fundamentals of modern methods for expanding the seismic record spectrum. "NSEIS" technology]. Geosochi – 2023. Aktual'nye problemy geologii i geofiziki: sb. konferencii [Geosochi − 2023. Actual problems of geology and geophysics: coll. art conference]. Tver, PolyPRESS publ., 2023. pp. 97–101 (In Russ)
15. Wei Li, Yuea D., Wua S. Thickness prediction for high-resolution stratigraphic interpretation by fusing seismic attributes of target and neighboring zones with an SVR algorithm. Marine and Petroleum Geology, 2020,vol. 113, pp. 1–14
16. Wu J., Yang J., Nakagoshi N., Lu X., Xu H., Prediction of sand thickness using seismic attributes based on BP-Neural Network. Advanced Materials Research, 2012, vol. 524–527, pp. 180–183
17. Wang Y.Y. Xu G., Pang X., A method for restoring sedimentary sequence original structural profiles: A case study of Miocene strata from the northern continental slope of the South China Sea. Marine and Petroleum Geology, 2019, vol. 103, pp. 294–305
18. Xu G., Haq B.U. Seismic facies analysis: Past, present and future. Earth-Science Reviews, 2022, vol. 224, no. 37, art. 103876
19. Platov B. V., Kadirov A. I., Zinyukov R. A., Minekaeva D. R. Podbor optimal'nykh parametrov rascheta tolshchiny malomoshchnykh plastov pri pomoshchi klassifikatsii po forme seysmotrassy [Selection of optimal parameters for the thin layers thickness calculation using waveform classification]. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Geologiya − Proceedings of Voronezh State University. Series: Geology, 2024, no. 3, pp. 114–120 (In Russ.)
20. Olneva T. V., Oreshkova M. Yu., Butorin A. V., Egorov A. S. Morfometricheskiy podkhod k kolichestvennoy otsenke moshchnosti otlozheniy meandriruyushchikh paleorusel tyumenskoy svity Zapadno-Sibirskogo neftegazonosnogo basseyna [A morphometric approach to quantitative assessment of the thickness of meandering paleochannel deposits of the Tyumen Formation in the West Siberian oil and gas basin]. Georesursy − Geo-resources, 2024, vol. 26, no. 3, pp. 143–150 (In Russ.)
21. Inzhenernaja geofizicheskaja laboratorija «IVANPLAB [Engineering Geophysical Laboratory "IVANPLAB"]. Available at: https://ivanplab.ru/ (accessed: 15.10.2024) (In Russ.)
22. Kruglov V. V., Borisov V. V. Iskusstvennye nejronnye seti: teorija i praktika [Artificial neural networks: theory and practice]. Moscow, Hotline-Telecom publ., 2002, 381 p. ISBN: 5-93517-103-1 (In Russ.)
23. Breiman L. Random Forests. Machine Learning, 2001, vol. 45, pp. 5–32
24. Priezzhev I.I., Danko D.A., Onischenko A.N. Ierarhicheskie neyronye seti v zadachah prognoza svoystv kollektorov nefti I gaza po skvazhinnym I seismicheskim dannym. [Hierarchical neural networks in problems of forecasting properties of oil and gas reservoirs from well and seismic data]. Geologiya i Geofizika − Geology and Geophysics, 2025, no. 1, pp.131−140 (In Russ.)
25. Priezzhev I. I., Danko D. A. Prognoz komponent ob"emnoy litologo-petrofizicheskoy modeli po kernovym dannym i GIS na osnove neyronnykh setey Kolmogorova s polnofunktsional'nymi aktivatsionnymi funktsiyami [Forecast of volumetric lithological and petrophysical model components based on core data and well logging using Kolmogorov neural networks with fully functional activation functions]. Geomodel': XXII nauchno-prakticheskaja konferencija po voprosam geologorazvedki i razrabotki mestorozhdenij nefti i gaza: sb. konferencii [Geomodel: XXII Scientific and Practical Conference on Geological Exploration and Development of Oil and Gas Fields: coll. art conference]. Gelendzhik publ., 2020, 53 p. (In Russ.)
