Physics-Informed Long-Range Coulomb Correction for Machine-learning Hamiltonians
This addresses a critical bottleneck for accurate simulations of polar materials and heterostructures in computational chemistry and materials science, representing a significant but incremental improvement over existing short-range models.
The paper tackled the omission of long-range Coulomb interactions in machine-learning electronic Hamiltonians, which cause errors in polar crystals and heterostructures, and showed that their physics-based correction method reduced errors by two- to threefold and eliminated staircase artifacts in benchmarks.
Machine-learning electronic Hamiltonians achieve orders-of-magnitude speedups over density-functional theory, yet current models omit long-range Coulomb interactions that govern physics in polar crystals and heterostructures. We derive closed-form long-range Hamiltonian matrix elements in a nonorthogonal atomic-orbital basis through variational decomposition of the electrostatic energy, deriving a variationally consistent mapping from the electron density matrix to effective atomic charges. We implement this framework in HamGNN-LR, a dual-channel architecture combining E(3)-equivariant message passing with reciprocal-space Ewald summation. Benchmarks demonstrate that physics-based long-range corrections are essential: purely data-driven attention mechanisms fail to capture macroscopic electrostatic potentials. Benchmarks on polar ZnO slabs, CdSe/ZnS heterostructures, and GaN/AlN superlattices show two- to threefold error reductions and robust transferability to systems far beyond training sizes, eliminating the characteristic staircase artifacts that plague short-range models in the presence of built-in electric fields.