Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements
By So Takamoto, C. Shinagawa, Daisuke Motoki, Kosuke Nakago, Wenwen Li, I. Kurata, Taku Watanabe, Yoshihiro Yayama, H. Iriguchi, Yusuke Asano and 12 more. Nature Communications, 2021
376 citations recorded by the source corpus.
Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. Here we report a development of universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, which include a diverse set of virtual structures used to attain the universality. We demonstrated the applicability of PFP in selected domains: lithium diffusion in LiFeSO4F, molecular adsorption in metal-organic frameworks, an order–disorder transition of Cu-Au alloys, and material discovery for a Fischer–Tropsch catalyst. They showcase the power of PFP, and this technology provides a highly useful tool for material discovery. Existing neural network potentials are generally designed for narrow target materials. Here the authors develop a neural network potential which is able to handle any combination of 45 elements and show its applicability in multiple domains.
Subfields: Materials Chemistry
View Paper: https://www.semanticscholar.org/paper/cc33ddc931cb3f709f7f6e9d4165cf8d98874f67
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Materials Chemistry
- A. Michaelides
- Christoph Schran
- Ilyes Batatia
- D. Kov'acs
- Volker L. Deringer
- Mark Asta
- Tejs Vegge
- Axel van de Walle
Citations in the corpus
- A foundation model for atomistic materials chemistry. (2023, positive): “To date, the most general and transferable force field for molecular dynamics is the PFP model ( 29 ) (TeaNet architecture ( 30 )), also proprietary (including its training set that covers 45 elements and is significantly larger than MP and also covers molecules and surfaces).”
- LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion (2025, unknown): “Specifically, the MACE-mh-1 model with OMAT PBE output head was employed[34, 41], augmented with a D3 dispersion correction using the Becke–Johnson damping scheme[42–44].”