Charting the chemical space of Zintl phases with graph neural networks and bonding insights
We combine graph neural networks and an upper bound energy minimization framework to explore >90 000 candidates, discovering 1810 stable Zintl phases with high precision and revealing the key role of ionic bonding in their stability.
Authors
- Cheng‐Wei Lee (ORCID: https://orcid.org/0000-0002-8317-588X)
- Prashun Gorai (ORCID: https://orcid.org/0000-0001-7866-0672)
- Jeffrey Law (ORCID: https://orcid.org/0000-0003-2828-1273)
- Svilen Bobev (ORCID: https://orcid.org/0000-0002-0780-4787)
- Qian Yang (ORCID: https://orcid.org/0000-0001-5519-1092)
- Rinkumoni Chaliha
- Manish Kumar Kothakonda
Institutions
- National Laboratory of the Rockies (US)
- University of Connecticut (US)
- Rensselaer Polytechnic Institute (US)
- Colorado School of Mines (US)
- University of Delaware (US)
Publication Details
- Journal
- Journal of Materials Chemistry A
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5ta06210a
- Citations
- 1
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.52
Funders
- National Science Foundation
- U.S. Department of Energy
- Office of Science
- Office of Energy Efficiency and Renewable Energy
- Division of Materials Research
- Basic Energy Sciences
- Office of Energy Efficiency
- National Renewable Energy Laboratory