Well Log-Guided Synthesis of Subsurface Images from Sparse Petrography Data Using cGANs
This work addresses reservoir characterization gaps for energy applications like carbon capture and hydrogen storage, though it is incremental as it applies an existing cGAN method to a new domain with specific data integration.
The paper tackles the problem of costly and sparse pore-scale imaging in subsurface formations by developing a conditional Generative Adversarial Network (cGAN) framework to synthesize realistic thin section images of carbonate rock formations, conditioned on porosity values from well logs, achieving 81% accuracy within a 10% margin of target porosity values.
Pore-scale imaging of subsurface formations is costly and limited to discrete depths, creating significant gaps in reservoir characterization. To address this, we present a conditional Generative Adversarial Network (cGAN) framework for synthesizing realistic thin section images of carbonate rock formations, conditioned on porosity values derived from well logs. The model is trained on 5,000 sub-images extracted from 15 petrography samples over a depth interval of 1992-2000m, the model generates geologically consistent images across a wide porosity range (0.004-0.745), achieving 81% accuracy within a 10\% margin of target porosity values. The successful integration of well log data with the trained generator enables continuous pore-scale visualization along the wellbore, bridging gaps between discrete core sampling points and providing valuable insights for reservoir characterization and energy transition applications such as carbon capture and underground hydrogen storage.