PIL-Net: a physics-informed graph convolutional network for predicting atomic multipoles
PIL-Net is a physics-informed graph convolutional network capable of predicting atomic multipole moments quickly and with high accuracy.
Authors
- Aurora E. Clark (ORCID: https://orcid.org/0000-0001-9381-721X)
- Alex Pothen (ORCID: https://orcid.org/0000-0002-3421-3325)
- Caitlin Whitter (ORCID: https://orcid.org/0000-0001-8746-3574)
Institutions
- Purdue University West Lafayette (US)
- University of Utah (US)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00228a
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Energy
- Purdue University
- Office of Science
- Lawrence Berkeley National Laboratory