Meta-LegNet learns transferable local adsorption environments via equivariant graph learning and meta-learning to predict sites and energies on catalyst surfaces without exhaustive enumeration.
Adsorbml: a leap in efficiency for adsorption energy calculations using generalizable machine learning potentials.npj Computational Materials, 9(1):172, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Meta-LegNet: A Transferable and Interpretable Framework for Surface Adsorption Prediction via Self-Defined Adsorption-Environment Learning
Meta-LegNet learns transferable local adsorption environments via equivariant graph learning and meta-learning to predict sites and energies on catalyst surfaces without exhaustive enumeration.