Borehole electrical imaging logs provide important sensor-derived information for identifying fractures, bedding structures, and reservoir heterogeneity. However, strip-like missing regions commonly arise from uneven tool pad distribution, incomplete borehole coverage, and acquisition limitations, which can distort geological structures and reduce interpretation reliability. Because the true values inside real missing regions are unobservable, complete ground-truth labels are generally unavailable. This study therefore proposes a real missing-region-constrained self-supervised inpainting framework for borehole electrical imaging logs. The key idea is to use real missing masks to define safe intact regions and to generate artificial strip-like training masks only within those reliable regions, thereby avoiding supervision contamination from originally missing or adjacent unstable areas. A UNet-based inpainting model is developed, and two attention-enhanced variants, UNet-SE and UNet-CBAM, are evaluated together with Telea and Navier–Stokes baselines. In addition to the main comparison, mask-level ablation, model-level ablation, repeated-seed robustness analysis, and lightweight expert-assisted geological assessment are used to examine the reliability of the proposed strategy. The results show that learning-based methods consistently outperform conventional approaches for structurally complex strip-like gaps. UNet-CBAM achieves the best overall performance, with mask-MAE, mask-PSNR, and mask-SSIM values of 14.8, 21.2 dB, and 0.8, respectively. The safe-region-constrained strategy further reduces supervision contamination and improves reconstruction quality compared with random or less restrictive mask-generation strategies. These findings indicate that the proposed framework offers a practical self-supervised solution for improving the quality and interpretability of sensor-captured borehole imaging logs when complete labels are unavailable.
Fractal analysis has been widely applied to characterize the complexity of pore systems in tight sandstone reservoirs. However, fractal parameters derived from different experimental techniques are frequently interpreted without sufficient consideration of their distinct physical meanings. In this study, tight sandstones from the Fuyu Formation in the Songliao Basin were investigated using cast thin sections, scanning electron microscopy, high–pressure mercury intrusion porosimetry, and nuclear magnetic resonance. The objective was to establish a comparative interpretation framework that distinguishes capillary–pressure–controlled geometric fractal dimensions from NMR–derived apparent relaxation–response fractal parameters (ARR fractal parameters). The pore–throat system is dominated by medium– to fine–sized throats, with the dominant pore–throat radii concentrated between 0.05 and 0.15 μm. Mercury–intrusion–derived fractal parameters primarily characterize the geometric heterogeneity of relatively large and fine pore–throat systems, whereas NMR–derived parameters mainly reflect the apparent relaxation response associated with pore–scale fluid occurrence rather than strict geometric complexity. In the present MICP–NMR subset, comparative regression trends indicate that the geometric fractal parameter representing fine pore throats is more responsive to median pore–throat radius and movable–fluid saturation, whereas the NMR–derived apparent relaxation–response parameter associated with longer relaxation times shows a relatively closer relationship with log–transformed permeability. These relationships should be regarded as exploratory response trends rather than universal predictive models. These findings demonstrate that the two types of fractal parameters provide complementary rather than interchangeable information for reservoir evaluation. The proposed comparative framework offers a physically constrained basis for integrating pore–throat geometry, relaxation response, fluid occurrence, and seepage properties in the characterization of tight sandstone reservoirs.