Table 2 Five model performance after the first transfer learning: buck-based NNP (DFT_res) with different charge schemes (Bader vs QEq)

From: Neural network potentials with effective charge separation for non-equilibrium dynamics of ionic solids: a ZnO case study

 

E (meV/atom)

F (meV/Å)

σ (MPa)

Bader Charge

52.9 (±0.6)

425.8 (±6.8)

520.2 (±30.5)

QEq

66.3 (±1.1)

402.9 (±9.3)

761.5 (±76.5)

  1. Qeq parameters are obtained from the previous study71.
Back to article page