Machine-learned exchange-correlation functionals for molecules, solids, and reactive surfaces
Abstract
The application of density functional theory to heterogeneous catalysis is hindered by the shortcomings of conventional density functional approximations. We combine machine learning with explicitly non-local physically informed descriptors and introduce an exchange-correlation functional (CIDER26SS) framework regularized for wide transferability. CIDER26SS is size-extensive, highly efficient, provides a balanced and accurate description of both molecular and solid-state systems, and is specifically well-optimized for transition metal surface chemistry. Surpassing existing conventional functionals, CIDER26SS resolves the CO/Pt puzzle, identifying the correct binding site for CO adsorption on the Pt(111) surface, along with an accurate adsorption energy, Pt lattice constant, and surface energy. Predictions agree well with the experimental values, even when all bulk and surface data for Pt are excluded from the training set. Remarkably, CIDER26SS exceeds the accuracy of semilocal approximations even for systems far outside the training domain.
Related
- Stationarity Constraints Improve Both Energies and Densities of Machine-Learned Exchange-Correlation Functionals
- Predicting Thermophysical Properties of Halide Salts Using On-the-Fly Machine-Learned Interatomic Potentials Across Multiple Exchange-Correlation Functionals
- Exchange-mediated spin–electric control of single molecules on surfaces
- Comparative Assessment of Exchange-Correlation Functionals for the Structural, Thermodynamic, and Transport Properties of Liquid Lithium
- Adding Temperature to the Adiabatic Connection: Hybrid Functionals for Static and Dynamic Correlation
BibTeX
@misc{abdallah2026machinelearned,
title = {{Machine-learned exchange-correlation functionals for molecules, solids, and reactive surfaces}},
author = {Mohamed S. Abdallah and Zhuotao Jin and Boris Kozinsky and Kyle Bystrom},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.21525},
eprint = {2608.21525},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.21525},
}
RIS
TY - UNPB
TI - Machine-learned exchange-correlation functionals for molecules, solids, and reactive surfaces
AU - Mohamed S. Abdallah
AU - Zhuotao Jin
AU - Boris Kozinsky
AU - Kyle Bystrom
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2608.21525
UR - https://arxiv.org/abs/2608.21525
AB - The application of density functional theory to heterogeneous catalysis is hindered by the shortcomings of conventional density functional approximations. We combine machine learning with explicitly non-local physically informed descriptors and introduce an exchange-correlation functional (CIDER26SS) framework regularized for wide transferability. CIDER26SS is size-extensive, highly efficient, provides a balanced and accurate description of both molecular and solid-state systems, and is specifically well-optimized for transition metal surface chemistry. Surpassing existing conventional functionals, CIDER26SS resolves the CO/Pt puzzle, identifying the correct binding site for CO adsorption on the Pt(111) surface, along with an accurate adsorption energy, Pt lattice constant, and surface energy. Predictions agree well with the experimental values, even when all bulk and surface data for Pt are excluded from the training set. Remarkably, CIDER26SS exceeds the accuracy of semilocal approximations even for systems far outside the training domain.
ER -