Deep-Learning-Based Workflow for Cavern Segmentation and Derived Profile Construction from Core Photos
Scientific Visualization · 2026-11 · 18 (3) · 41-51
DOI: 10.26583/sv.18.3.04 ↗Kurz gefasst
Fachartikel in der Zeitschrift Scientific Visualization, 2026-11. Verfasst von D.O. Makienko und 4 weiteren Autor:innen.
Abstract (Originalsprache)
To estimate hydrocarbon reserves and plan production, geologists construct reservoir models that describe lithofacies variations with depth. In carbonate rocks, caverns provide important information about storage capacity and fluid flow potential. Photographs of core samples allow analysis of surface-visible caverns. Segmentation of cavern-like objects in core photographs enables profile construction to identify depth intervals where lithofacies change, reflecting variations in sedimentation conditions and corresponding reservoir properties. Rock heterogeneity, varying imaging conditions, and non-target structures such as fractures and artifacts complicate cavern analysis from photographs. This paper proposes a deep-learning-based workflow for segmentation of cavern-like objects for visu-alization of the cavernosity profile intended to support lithofacies delineation. The work-flow includes semi-automatic annotation preparation for training a deep learning segmen-tation model. Model training relies on augmented images to account for varying bright-ness distributions. The segmentation results enable visualization of the depth-dependent profile that qualitatively reflects the distribution of cavern-like objects and may support description and delineation of lithofacies.
Zitieren
APA
Makienko, D., Kossov, G., Abashkin, V., Seleznev, I., & Safonov, I. (2026). Deep-Learning-Based Workflow for Cavern Segmentation and Derived Profile Construction from Core Photos. Scientific Visualization, 18(3), 41-51. https://doi.org/10.26583/sv.18.3.04
Vancouver
Makienko D, Kossov G, Abashkin V, Seleznev I, Safonov I. Deep-Learning-Based Workflow for Cavern Segmentation and Derived Profile Construction from Core Photos. Scientific Visualization. 2026;18(3):41-51. doi:10.26583/sv.18.3.04
BibTeX
@article{Makienko2026,
author = {Makienko, D.O. and Kossov, G.A. and Abashkin, V.V. and Seleznev, I.A. and Safonov, I.V.},
title = {Deep-Learning-Based Workflow for Cavern Segmentation and Derived Profile Construction from Core Photos},
journal = {Scientific Visualization},
year = {2026},
volume = {18},
number = {3},
pages = {41--51},
doi = {10.26583/sv.18.3.04}
}
EUVIMED