Machine Learning-Based Well Design to Enhance Unconventional Energy Production
The DIFFERENTIATE program seeks to leverage the emerging artificial intelligence (AI) revolution to help resolve the energy and environmental challenges of our time. The program aims to speed energy innovation by incorporating machine learning (ML) into the energy technology development process. A core part of AI, ML is the study of computer algorithms that improve automatically through experience. This approach is expected to facilitate a rapid transition to lower-carbon-footprint energy sources and systems. To organize the proposed efforts, the program uses a simplified engineering design process framework to conceptualize several ML tools that could help engineers execute and solve these problems in a manner that dramatically accelerates the pace of energy innovation.
Project Innovation + Advantages:
Los Alamos National Laboratory (LANL) seeks to increase the efficiency with which oil and gas are extracted from unconventional reservoirs while reducing the environmental impact of such processes. Current hydrofracturing-enabled extraction efficiencies are only 5 to 10%. LANL seeks to improve upon these levels by developing physics-informed machine learning (ML) based models from field data to discover effective well design characteristics. LANL will use its ML framework, which is based on recent advances in ML, differentiable programming, and cloud computing, to extract actionable information to enhance energy production while mitigating its environmental impact. Current baseline well design testing takes about 4 years and costs more than $6M per well. LANL predicts that if completely deployed, it is expected that the proposed framework will reduce the time and cost of well design by 40% and energy extraction can be tripled.
DIFFERENTIATE aims to enhance the productivity of energy engineers in helping them to develop next-generation energy technologies. If successful, DIFFERENTIATE will yield the following benefits in ARPA-E mission areas:
Seek U.S. technological competitive advantage by leading the development of machine-learning enhanced engineering design tools.
Use these tools to solve our most challenging energy and environmental problems by facilitating an economically-attractive transition to lower carbon-footprint energy sources and systems.
Reap the economic productivity benefits associated with the commercial adoption of the resulting higher-value energy technologies and associated products.
ARPA-E Program Director:
Dr. David TewProject Contact:
Press and General Inquiries Email:
ARPA-E-Comms@hq.doe.govProject Contact Email:
University of New Mexico
Julia Computing, Inc.
University of Texas, Austin
Massachusetts Institute of Technology
Chevron Energy Technology Company