Quantitative workflows utilizing real-time data to constrain uncertainty have the potential to significantly improve geosteering. Fast updates based on real-time data are particularly important when drilling in complex reservoirs with high uncertainties in pre-drill models. However, practical assimilation of real-time data requires effective geological modelling and mathematically robust parameterization. We propose a generative adversarial deep neural network (GAN), which is trained to reproduce geologically consistent 2D sections of fluvial successions. Offline training produces a fast GAN-based approximation of complex geology parameterized as a 60-dimensional model vector with standard Gaussian distribution of each component. Probabilistic forecasts are generated using an ensemble of equiprobable model vector realizations. A forward-modelling sequence, including a GAN, converts the initial (prior) ensemble of realizations into EM log predictions. An ensemble smoother minimizes statistical misfits between predictions and real-time data, yielding an update of model vectors and reduced uncertainty around the well. Updates can then be translated to probabilistic predictions of facies and resistivities. This paper demonstrates a workflow for geosteering in an outcrop-based synthetic fluvial succession. In our example, the method reduces uncertainty and correctly predicts most of the major geological features up to 500 m ahead of drill-bit. The condensed summary is also submitted for presentation at the 3rd EAGE/SPE Geosteering Workshop to be held 2-4 November 2021, online.
ASJC Scopus subject areas