Towards universal neural network interatomic potential
Source abstract
Abstract
• Universal interatomic potential for modeling chemically and structurally complex systems. • Tensorial message passing in equivariant graph convolutional network. • Iterative construction of a diverse and broad training dataset. • User-friendly atomistic simulation platform Matlantis™ powered by universal interatomic potential for 72 elements.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Electron and X-Ray Spectroscopy Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (17)
Show source-provided references
1. High accuracy neural network interatomic potential for NiTi shape memory alloy10.1016/j.actamat.2022.118217 ↗
2. Development of robust neural-network interatomic potential for molten salt10.1016/j.xcrp.2021.100359 ↗
3. Modeling LiF and FLiBe molten salts with robust neural network interatomic potential10.1021/acsami.1c00604 ↗
4. Performance and cost assessment of machine learning interatomic potentials10.1021/acs.jpca.9b08723 ↗
5. Teanet: universal neural network interatomic potential inspired by iterative electronic relaxations
6. Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements10.1038/s41467-022-30687-9 ↗
7. Huerta · 2022
8. Molecular dynamics of electric-field driven ionic systems using a universal neural-network potential
9. Machine learning of accurate energy-conserving molecular force fields10.1126/sciadv.1603015 ↗
10. Quantum chemistry structures and properties of 134 kilo molecules10.1038/sdata.2014.22 ↗
11. The Materials Project: a materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
12. Open catalyst 2020 (oc20) dataset and community challenges10.1021/acscatal.0c04525 ↗
13. Active learning of uniformly accurate interatomic potentials for materials simulation10.1103/PhysRevMaterials.3.023804 ↗
14. So · 2022 · 4
15. Interfacial plasticity governs strain rate sensitivity and ductility in nanostructured metals10.1073/pnas.0611097104 ↗
16. Machine learning in nuclear materials research10.1016/j.cossms.2021.100975 ↗
17. A New Zinc Salt Chemistry for Aqueous Zinc-Metal Batteries