Science-Informed Machine Learning to Accelerate Real-time (SMART) Decisions in Subsurface Applications Phase 2 Development and Field Validation

Researcher(s)

Sponsoring Agency
Leidos, Inc.

Summary

The primary goal of the SMART initiative is to transform reservoir management via improvements in subsurface visualization and through development and application of state-of-the-art machine learning (ML) techniques to achieve speed and enhanced detail for predicting CO2 transport in the subsurface. The goal of Phase 2 is to develop site-specific science-informed machine learning tools for accelerated deployment and monitoring of CO2 storage in sites across the U.S. and the world. More specifically, the goal of Phase 2C where this team at PSU will be contributing is to demonstrate how the suite of MLassisted tools and workflows from Phase 1 can be applied to improve data interpretation and forward modeling to support (near) real-time operational decision-making for a project undergoing active CO2 injection.

Term
 -