Origins of Universal Machine Learning Force-Field Errors in Multicomponent Materials
Universal machine learning force-field generalization to multicomponent environments generated by compositional design remains insufficiently assessed.
ProofPaper ↗
Key points
- We construct a benchmark of 7,599 multicomponent configurations inspired by high-entropy design, elemental substitution and anion mixing.
- Eleven pretrained models are evaluated against density functional theory for energies, forces and stresses, with assessment extended to elastic, vibrational and adsorption-related properties.
- Force errors are analysed through training-reference coverage, local geometric heterogeneity, distance directionality and elemental response.
- Fitting difficulty in independent elemental systems correlates with electronic band-energy responses to atomic displacements and Fermi-level shifts, and a similar pattern is observed in multicomponent systems.
Sources (1)
- [1]Origins of Universal Machine Learning Force-Field Errors in Multicomponent MaterialsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 11:01 AM
Universal machine learning force-field generalization to multicomponent environments generated by compositional design remains insufficiently assessed.
We construct a benchmark of 7,599 multicomponent configurations inspired by high-entropy design, elemental substitution and anion mixing.
Extractive summary: sentences quoted from the sources.