LES augments short-range MLIPs with long-range electrostatics learned from energies and forces alone, improving accuracy and enabling Born effective charge and dipole prediction.
Physnet: A neural network for predicting energies, forces, dipole moments, and partial charges,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.chem-ph 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials
LES augments short-range MLIPs with long-range electrostatics learned from energies and forces alone, improving accuracy and enabling Born effective charge and dipole prediction.