Comparison of ML-Based Proxy Modeling Strategies: Lessons Learned from the SMART Initiative
Teams of researchers on Task 5 of the SMART project have developed a variety of modeling architectures to predict subsurface behavior during carbon injection and post-injection periods. One important part of this task was to compare the candidate approaches in terms of accuracy, reliability, speed, and memory use, all using a common set of metrics and visualizations for an “apples to apples” comparison. Dr. Jared Schuetter will share the details of this task, the results that were obtained, and the lessons learned.
Authors
- Jared Schuetter (ORCID: https://orcid.org/0000-0003-0818-6076)
- Seyyed A. Hosseini (ORCID: https://orcid.org/0000-0002-3344-6274)
- Paul Holcomb (ORCID: https://orcid.org/0000-0002-5572-7480)
- Alex Tartakovsky
- Hongkyu Yoon (ORCID: https://orcid.org/0000-0001-6719-280X)
- Christian Munoz Oro
- Hongsheng Wang (ORCID: https://orcid.org/0000-0001-6977-3181)
- Meen Kadeethum
- Chung Yan Shih (ORCID: https://orcid.org/0000-0002-7140-2926)
Institutions
- Battelle (US)
- University of Illinois System (US)
- Sandia National Laboratories (US)
- National Energy Technology Laboratory (US)
- The University of Texas at Austin (US)
Publication Details
- Published
- 2024-08-05
- DOI
- https://doi.org/10.2172/2426322
- Primary Topic
- Access Control and Trust
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Energy
- National Energy Technology Laboratory