Verification of a real-time ensemble-based method for updating earth model based on GAN

Abstract

The complexity of geomodelling workflows is a limiting factor for quantifying and updating uncertainty in real-time during drilling. We propose Generative Adversarial Networks (GANs) for parametrization and generation of geomodels, combined with Ensemble Randomized Maximum Likelihood (EnRML) for rapid updating of subsurface uncertainty. This real-time ensemble method combined with a highly non-linear model arising from neural-network modeling sequences might produce inaccurate and/or biased posterior solutions. This paper illustrates the predictive ability of EnRML on several examples where we assimilate local extra-deep electromagnetic logs. Statistical verification with MCMC confirms that the proposed workflow can produce reliable results required for geosteering wells.

Submitted to Journal of Computational Science. arXiv admin note: substantial text overlap with arXiv:2104.02550

References in corpus (2)

• Probabilistic model-error assessment of deep learning proxies: an application to real-time inversion of borehole electromagnetic measurements
• Probabilistic forecasting for geosteering in fluvial successions using a generative adversarial network

Cited by in corpus (1)

• Strategic Geosteering Workflow with Uncertainty Quantification and Deep Learning: A Case Study on the Goliat Field