A Data-driven Approach to Model Viscous Fingering in Imbibition vs. Drainage at the Pore Scale

After primary oil production stage, reservoir energy is depleted. At this stage, the reservoir needs to be re-energized through enhanced oil recovery techniques. In these techniques, an external fluid is injected into the reservoir to displace oil in place towards the production wells. Water is the most common fluid used in enhanced oil recovery processes. Parameters such as water viscosity, oil in place viscosity, reservoir rock wetting state, water injection velocity, etc. critically affect the water flow pathways during flow in a reservoir. This research aims to understand the effect of these parameters on the pattern of water flow in porous media. We apply microfluidic (pore scale) approach to visualize the water pathways and perform a sensitivity analysis to understand the effect of the mentioned parameters on the efficiency of water injection processes. We apply Artificial intelligence (AI) techniques to model and understand the physics behind the pore scale observations.

Faculty Supervisor:

Peter Englezos;Bhushan Gopaluni

Student:

Danial Arab

Partner:

PERM

Discipline:

Engineering - chemical / biological

Sector:

University:

University of British Columbia

Program: