Can Polat pronounced “John”
2025 · Computational Materials Science

QuantumShellNet: Ground-state eigenvalue prediction of materials using electronic shell structures and fermionic properties via convolutions

Can Polat , Hasan Kurban , Mustafa Kurban
TL;DR

An equivariant convolutional network that predicts ground-state eigenvalues of materials directly from electronic shell structures. Outperforms DFT for the same regime at a fraction of the compute, and beats modern neural-wavefunction baselines like PsiFormer and FermiNet on our benchmark.

Cite
@article{polat2025quantumshellnet,
  title = {QuantumShellNet: Ground-state eigenvalue prediction of materials using electronic shell structures and fermionic properties via convolutions},
  author = {Can Polat and Hasan Kurban and Mustafa Kurban},
  year = 2025,
  journal = {Computational Materials Science},
  doi = {10.1016/j.commatsci.2024.113366},
}