{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/conditioning-of-three-dimensional-generative","title":"Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models","arxiv_id":"1802.05622","date":"2018-02-15","proceeding":null,"authors":["Lukas Mosser","Olivier Dubrule","Martin J. Blunt"],"abstract":"Geostatistical modeling of petrophysical properties is a key step in modern\nintegrated oil and gas reservoir studies. Recently, generative adversarial\nnetworks (GAN) have been shown to be a successful method for generating\nunconditional simulations of pore- and reservoir-scale models. This\ncontribution leverages the differentiable nature of neural networks to extend\nGANs to the conditional simulation of three-dimensional pore- and\nreservoir-scale models. Based on the previous work of Yeh et al. (2016), we use\na content loss to constrain to the conditioning data and a perceptual loss\nobtained from the evaluation of the GAN discriminator network. The technique is\ntested on the generation of three-dimensional micro-CT images of a Ketton\nlimestone constrained by two-dimensional cross-sections, and on the simulation\nof the Maules Creek alluvial aquifer constrained by one-dimensional sections.\nOur results show that GANs represent a powerful method for sampling conditioned\npore and reservoir samples for stochastic reservoir evaluation workflows.","url_abs":"http://arxiv.org/abs/1802.05622v1","url_pdf":"http://arxiv.org/pdf/1802.05622v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"conditioning-of-three-dimensional-generative","repo_url":"https://github.com/LukasMosser/geogan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}