Stanford University

CCSNet: A deep learning modeling suite for CO2 storage Webinar Event

Wednesday, Oct 6, 2021 12:00 PM
More Info:
CCSNet: A deep learning modeling suite for CO2 storage Webinar Event

RSVP for this event

Faculty/Staff, Students, Alumni/Friends, Members
Energy Resources Engineering

The referenced media source is missing and needs to be re-embedded.

Numerical simulation is an essential tool for many applications involving subsurface flow and transport, yet often suffers from computational challenges due to the multi-physics nature, highly non-linear governing equations, inherent parameter uncertainties, and the need for high spatial resolutions to capture multi-scale heterogeneity. We developed CCSNet, a general-purpose deep-learning modeling suite that can act as an alternative to conventional numerical simulators for carbon capture and storage (CCS) problems where CO2 is injected into saline aquifers in 2d-radial systems. CCSNet consists of a sequence of deep learning models producing all the outputs that a numerical simulator typically provides, including saturation distributions, pressure buildup, dry-out, fluid densities, mass balance, solubility trapping, and sweep efficiency. The results are 1,000 to 10,000 times faster than conventional numerical simulators. As an application of CCSNet illustrating the value of its high computational efficiency, we developed rigorous estimation techniques for the sweep efficiency and solubility trapping.

IconsList of icons used on the sitemaillinkedindouble carrot leftarrow leftdouble carrotplayerinstagramclosecarrotquotefacebooktwitterplusminussearchmenuarrowcloudclock