A theory-infused graph neural network predicts transition-metal alloy cohesive energies to within 10 meV per atom and attributes single-atom alloy agglomeration to d-orbital coupling and segregation to delocalized electron effects.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decoding the Stability of Transition-Metal Alloys with Theory-infused Deep Learning
A theory-infused graph neural network predicts transition-metal alloy cohesive energies to within 10 meV per atom and attributes single-atom alloy agglomeration to d-orbital coupling and segregation to delocalized electron effects.