EUVIMEDEUVIMED entdecken
Crossref

Reinforcement-Learning Tracking of Seismic Horizons From Sparse Expert Interpretation: A Case Study on the Achimov Clinoform Deposits of Northern West Siberia

D. A. Bogoedov, N. S. Bezukhov, A. I. Pavliuk, P. A. Avdeev, A. K. Bazanov, I. I. Efremov, R. R. Shakirov, M. Yu. Shapovalo

Georesursy · 08.10.2026 · 28 (3) · 107-116

DOI: 10.18599/grs.2026.3.15 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Georesursy, online erschienen am 08.10.2026. Verfasst von D. A. Bogoedov und 7 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structural correlation of reflection horizons remains one of the most labour-intensive operations in 3D seismic interpretation, particularly within the clinoform Neocomian sections of West Siberia, where target reflections show variable dynamics, pinch-outs and are complicated by faulting. Because horizon tracking is inherently sequential, we formulate it as a Markov decision process and solve it with reinforcement learning. Observing a local seismic context and the history of previously picked samples, an agent chooses, at each step, the vertical shift of the horizon on the adjacent trace; the reward function encodes geophysical criteria – waveform similarity to the reference reflection, phase consistency, lateral smoothness and fault tolerance. The method is implemented as a two-stage scheme: a policy first correlates the horizon over a grid of reference sections with a user-defined spacing, building a reliable network of anchors, and then densifies the result into a continuous surface across the whole volume. The agent is trained in a synthetic environment produced by forward full-wavefield modelling, with imitation pretraining on reference horizon trajectories; one or two intersecting reference sections suffice as input, and additional interpretation is introduced in complex zones. Tested on Achimov deposits of a field in Northern West Siberia, the approach agrees with manual correlation within 10 ms over conformable intervals. Limitations and directions for development are discussed.

Zitieren

APA

Bogoedov, D. A., Bezukhov, N. S., Pavliuk, A. I., Avdeev, P. A., Bazanov, A. K., Efremov, I. I., Shakirov, R. R., & Shapovalo, M. Y. (2026). Reinforcement-Learning Tracking of Seismic Horizons From Sparse Expert Interpretation: A Case Study on the Achimov Clinoform Deposits of Northern West Siberia. Georesursy, 28(3), 107-116. https://doi.org/10.18599/grs.2026.3.15

Vancouver

Bogoedov DA, Bezukhov NS, Pavliuk AI, Avdeev PA, Bazanov AK, Efremov II, et al. Reinforcement-Learning Tracking of Seismic Horizons From Sparse Expert Interpretation: A Case Study on the Achimov Clinoform Deposits of Northern West Siberia. Georesursy. 2026;28(3):107-116. doi:10.18599/grs.2026.3.15

BibTeX
@article{Bogoedov2026,
  author = {Bogoedov, D. A. and Bezukhov, N. S. and Pavliuk, A. I. and Avdeev, P. A. and Bazanov, A. K. and Efremov, I. I. and Shakirov, R. R. and Shapovalo, M. Yu.},
  title = {Reinforcement-Learning Tracking of Seismic Horizons From Sparse Expert Interpretation: A Case Study on the Achimov Clinoform Deposits of Northern West Siberia},
  journal = {Georesursy},
  year = {2026},
  volume = {28},
  number = {3},
  pages = {107--116},
  doi = {10.18599/grs.2026.3.15}
}
Kostenlos starten →