EUVIMEDEUVIMED entdecken
Crossref

A two-branch convolutional neural network for pre-stack elastic parameter inversion of coal-bearing gas reservoirs

Fei Li, Mengbo Zhang, Qiang Liang, Xiaojie Cui, Na Ni, Qingzhou Zhang, Yongheng Zhang

Journal of Seismic Exploration · 23.04.2026 · 35 (2) · 025390076

DOI: 10.36922/jse025390076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Seismic Exploration, online erschienen am 23.04.2026. Verfasst von Fei Li und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate estimation of Poisson’s ratio is essential for the characterization of coal-bearing gas reservoirs, particularly in thin-bed and low signal-to-noise ratio environments where conventional elastic impedance (EI) inversion suffers from wavelet interference, limited resolution, and reliance on linearization assumptions. To address these limitations, we develop a physics-guided two-branch convolutional neural network (TB-CNN) that directly predicts Poisson’s ratio by jointly integrating EI-inverted P-wave velocity, S-wave velocity, and density with small-, medium-, and large-angle seismic stacks. The first branch provides geologically consistent, physics-informed background trends, while the second branch captures thin-bed-sensitive reflectivity features and amplitude tuning effects. The fused latent representation is explicitly regularized using empirical rock-physics relationships to ensure physical plausibility and enhanced generalization. Field validation on the 8# coal seam of the Ordos Basin demonstrates that the proposed TB-CNN improves vertical resolution, sharpens seam boundary delineation, and better preserves thickness variations compared with EI inversion and a single-branch CNN. Near-well comparisons show higher correlation with log-derived Poisson’s ratio, while lateral slices reveal improved continuity and thin-layer detectability. These results confirm that combining physics-guided stability with data-driven resolution provides a robust and interpretable framework for Poisson’s ratio inversion in thin coal seams and holds promise for broader applications in unconventional gas reservoir prediction.

Zitieren

APA

Li, F., Zhang, M., Liang, Q., Cui, X., Ni, N., Zhang, Q., & Zhang, Y. (2026). A two-branch convolutional neural network for pre-stack elastic parameter inversion of coal-bearing gas reservoirs. Journal of Seismic Exploration, 35(2), 025390076. https://doi.org/10.36922/jse025390076

Vancouver

Li F, Zhang M, Liang Q, Cui X, Ni N, Zhang Q, et al. A two-branch convolutional neural network for pre-stack elastic parameter inversion of coal-bearing gas reservoirs. Journal of Seismic Exploration. 2026;35(2):025390076. doi:10.36922/jse025390076

BibTeX
@article{Li2026,
  author = {Li, Fei and Zhang, Mengbo and Liang, Qiang and Cui, Xiaojie and Ni, Na and Zhang, Qingzhou and Zhang, Yongheng},
  title = {A two-branch convolutional neural network for pre-stack elastic parameter inversion of coal-bearing gas reservoirs},
  journal = {Journal of Seismic Exploration},
  year = {2026},
  volume = {35},
  number = {2},
  pages = {025390076},
  doi = {10.36922/jse025390076}
}
Kostenlos starten →