Skip to content
Events
Students showcasing research posters at the 2015 GCEP Symposium

ERE Seminar: Gowri Srinivasan, LANL — Predictions of flow and transport in fractured media in the subsurface using graph-based machine learning

March 12, 2018 -
12:30pm to 1:30pm
Room 104, Green Earth Sciences Building, 367 Panama Street, Stanford
Event Sponsor: 
Energy Resources Engineering
Contact Email: 
jpcastro@stanford.edu

Predictions of flow and transport in fractured media in the subsurface using graph-based machine learning

Gowri SrinivasanLos Alamos National Laboratory | LANL

Flow through fractured media in the sub-surface is heavily dependent on microstructural information. Continuum models often eliminate features critical to accurately predicting macroscale behavior but are commonly used since resolving thousands of  fractures individually is computationally intractable. We overcome this hurdle by developing compact graph representations of the fracture networks, and using machine learning algorithms to mimic the detailed physics at the microscale. The resulting workflow has been shown to achieve up to 4 orders of magnitude computational speedup while maintaining accuracy.

Contact Phone: 
650.725.9835