Acoustic impedance to outcrop: Presenting near-surface seismic data as a virtual outcrop in carbonate analog studies

Outcrop analogs play a central role in understanding subseismic interwell depositional facies heterogeneity of carbonate reservoirs. geologists rarely utilize near-surface seismic data due to the limited vertical resolution and difficulty visualizing signals as “band-limited rocks.” This study proposes methodology using combination forward modeling conditional generative adversarial network (cGAN) translate seismic-derived acoustic impedance (AI) into pseudo-high-resolution virtual outcrop. We tested on Hanifa reservoir analog outcropping Wadi Birk, Saudi Arabia. interpret 4 km long outcrop photomosaic from digital model (DOM) for its facies, populate DOM with AI properties, calculate band-limited colored inversion. pair synthetic train them cGAN. Similarly, we photos chain two trained networks apply approximately 600 m acquired just behind The result translates images “behind-the-outcrop” model. is visual medium that operates at format more familiar geologists. resolves stratigraphic features such intricate downlap-onlap stratal termination scales tens centimeters outline buildup which are otherwise unresolvable AI.