General Learning of the Electric Response of Inorganic Materials
- 1University College London
- 2Imperial College London
Abstract
Dielectric response governs how materials interact with electric fields and light. Still, first-principles prediction of polarization P , Born effective charges Z * , and polarizability α remains too costly for large-scale screening and long-time dynamics. We introduce , a field-aware, O ( 3 ) -equivariant interatomic potential that learns a single electric-enthalpy functional F ( { R } , E ) and obtains P , Z * , and α by exact differentiation. A uniform field couples to latent equivariant features inside the backbone, while the scalar energy readout preserves Maxwell reciprocity, the acoustic sum rule, and crystal tensor symmetries by construction. Because this coupling is a plug-in on top of standard , existing energy/force foundation models can be upgraded to become field aware. Benchmarked against semilocal density-functional theory (DFT)/density-functional perturbation theory (DFPT) reference data, a directly trained cross-chemistry ferroelectric model reproduces the same-branch Berry phase and spontaneous polarizations across diverse inorganic crystals. Starting from the multihead foundation model and its Open Materials 2024 (OMAT)-Perdew-Burke-Ernzerhof (PBE) head, joint fine-tuning on dielectric, ferroelectric, and replay data yields foundation models, which predict Z * , α , derived dielectric constants, and cross-chemistry polarization trends with fidelity that captures branch-resolved polarization and spontaneous polarization, while retaining strong force-field accuracy. Further, single-material models and reproduce BaTiO 3 hysteresis loops and α -quartz infrared, Raman, and dielectric spectra from finite-field molecular dynamics, comparable to DFPT. These results show that a simple, physics-informed field coupling can endow atomistic foundation models with transferable dielectric and ferroelectric response, while targeted single-material training remains advantageous for the most quantitative spectroscopic predictions.
Related
- NEP89: universal neuroevolution potential for inorganic and organic materials across 89 elements
- Reproducibility of Thermodynamic Stability and Band-Gap Screening of Inorganic Materials Across Materials Project Versions
- Mechanoluminescence in crystalline inorganic materials: local disorder and the elastic distortion hypothesis
- Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning
- Harnessing polymeric materials for applications in electric vehicle with sustainability contributions and prospects
BibTeX
@article{martin2026general,
title = {{General Learning of the Electric Response of Inorganic Materials}},
author = {Bradley A. A. Martin and Alex M. Ganose and Venkat Kapil and Tingwei Li and Keith T. Butler},
journal = {PRX Intelligence},
year = {2026},
month = jul,
doi = {10.1103/b116-xy8k},
url = {https://doi.org/10.1103/b116-xy8k},
note = {CC BY},
}
RIS
TY - JOUR
TI - General Learning of the Electric Response of Inorganic Materials
AU - Bradley A. A. Martin
AU - Alex M. Ganose
AU - Venkat Kapil
AU - Tingwei Li
AU - Keith T. Butler
PY - 2026
DA - 2026/07/28
JO - PRX Intelligence
DO - 10.1103/b116-xy8k
UR - https://doi.org/10.1103/b116-xy8k
AB - Dielectric response governs how materials interact with electric fields and light. Still, first-principles prediction of polarization P , Born effective charges Z * , and polarizability α remains too costly for large-scale screening and long-time dynamics. We introduce , a field-aware, O ( 3 ) -equivariant interatomic potential that learns a single electric-enthalpy functional F ( { R } , E ) and obtains P , Z * , and α by exact differentiation. A uniform field couples to latent equivariant features inside the backbone, while the scalar energy readout preserves Maxwell reciprocity, the acoustic sum rule, and crystal tensor symmetries by construction. Because this coupling is a plug-in on top of standard , existing energy/force foundation models can be upgraded to become field aware. Benchmarked against semilocal density-functional theory (DFT)/density-functional perturbation theory (DFPT) reference data, a directly trained cross-chemistry ferroelectric model reproduces the same-branch Berry phase and spontaneous polarizations across diverse inorganic crystals. Starting from the multihead foundation model and its Open Materials 2024 (OMAT)-Perdew-Burke-Ernzerhof (PBE) head, joint fine-tuning on dielectric, ferroelectric, and replay data yields foundation models, which predict Z * , α , derived dielectric constants, and cross-chemistry polarization trends with fidelity that captures branch-resolved polarization and spontaneous polarization, while retaining strong force-field accuracy. Further, single-material models and reproduce BaTiO 3 hysteresis loops and α -quartz infrared, Raman, and dielectric spectra from finite-field molecular dynamics, comparable to DFPT. These results show that a simple, physics-informed field coupling can endow atomistic foundation models with transferable dielectric and ferroelectric response, while targeted single-material training remains advantageous for the most quantitative spectroscopic predictions.
SN - 3070-0329
ER -