Introduction

DOE FE NETL Science-Informed Machine Learning for Accelerating Real Time Decisions in Subsurface Applications (SMART) Initiative Phase 1

Machine-learning based data assimilation for CO2 storage sites.

DOE FE NETL Science-Informed Machine Learning for Accelerating Real Time Decisions in Subsurface Applications (SMART) Initiative Phase 1

Machine-learning based data assimilation for CO2 storage sites.

SPONSOR:
DOE (through subcontract with Sandia National Laboratories)

PROJECT PERIOD:
05/2020 – 09/2021

ABSTRACT:
We will develop and apply deep machine learning methods to predict CO2 flow and pressure distribution for geologic carbon storage. In particular, we will pursue advanced methods to incorporate real-time observation data into machine learning prediction. The proposed method will allow fast and reliable data assimilation of spatial and temporal observations.

PRINCIPAL INVESTIGATOR