Pore-Scale Characterization of Remaining Oil Evolution During Waterflooding in Offshore Sandstone Reservoirs Using Micro-CT and U-Net Semantic Segmentation

作者：Wensheng Zhou, C Y Liu, D G Wang, Chi Zhang, Wenhui Gao, Yushan Ma, Yuxin Zhang, Yaopan Yu · 发表于：Energies · 年份：2026 · DOI：10.3390/en19153518 · 研究领域：Enhanced Oil Recovery Techniques、Reservoir Engineering and Simulation Methods、Hydrocarbon exploration and reservoir analysis

After offshore sandstone reservoirs enter the high-water-cut development stage, remaining oil gradually changes from a continuously movable state to a dispersed, isolated, and locally trapped state. Therefore, pore-scale dynamic characterization of remaining oil is important for clarifying its occurrence state and identifying potential targets for further recovery. In this study, natural cores from a typical offshore continental sandstone reservoir were used to conduct micro-computed tomography (micro-CT) scanning experiments at different waterflooding stages. Fine identification of the rock skeleton, water phase, and remaining oil, as well as segmentation of remaining-oil units, was achieved using U-Net semantic segmentation and three-dimensional digital image reconstruction. Multiple parameters were extracted, including volume, surface area, equivalent diameter, major-axis length, intermediate-axis width, minor-axis thickness, shape factor, and Euler number. Combined with manually labeled results of typical remaining-oil unit, a decision-tree method was used to establish classification criteria for remaining-oil occurrence states. The results showed that, with increasing pore volumes injected (PV), remaining oil gradually evolved from an initially large-scale and continuously connected state to a small-scale dispersed trapping. The surface area and volume of remaining oil continuously decreased. Meanwhile, the shape factor decreased, and the Euler number increased, indicati...