Full text loading...
-
Deep-Learning Solutions for Seismic Reservoir Characterization: Where Do We Stand?
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 83rd EAGE Annual Conference & Exhibition, Jun 2022, Volume 2022, p.1 - 5
Abstract
Machine-Learning techniques are becoming very popular in the field of Gesciences as fast and powerful prediction tools for a variety of applications. Even if they do not seem ready to replace conventional tools, they can quickly bring valuable information at early stages of Exploration and Production projects. This paper aims at showing our investigations in applying an in-house machine-learning algorithm at different steps of the Seismic Reservoir Characterization workflow. After briefly presenting this deep-learning tool, we will show where it can be used in this workflow and we will analyze how it could support classical deterministic inversion and classification methodologies. Numerical tests on real datasets will exhibit the potential of our newly developed approaches in producing quick-look results which can help the interpreters for a faster and more efficient first evaluation of reservoirs.