Topology-aware E(3)-equivariant learning for physically consistent piezoelectric tensor prediction
Accurate prediction of piezoelectric tensors in crystals remains challenging because valid responses must satisfy both continuous geometric symmetries and discrete crystallographic constraints under periodic boundary conditions. Existing learning-based approaches typically emphasize equivariance or periodic geometry, b...
Ruihan Liu, Jianbo Yu, Yu Ji et al.
· npj Computational Materials · 0 citations