Stable and transferable exchange–correlation potentials via machine-learned density-independent mapping
- 2 October 2026
- journal article
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 165 (13)
Abstract
We present a machine-learning framework, density-independent mapping for exchange–correlation, for incorporating XC effects into density functional theory via a density-independent mapping from the external potential to the XC potential. By predicting the ground-state XC potential in a one-shot manner and holding it fixed throughout the self-consistent field (SCF) procedure, the approach entirely eliminates the need to evaluate the XC potential on the iteratively updated electron density, thereby enhancing numerical stability and efficiency. The model is implemented using kernel ridge regression and trained on a set of small neutral closed-shell molecular systems, representative of common chemical bonding motifs, achieving the predictive accuracy of hybrid functionals—with energy errors on the order of 10−3 kcal/mol—while bypassing expensive, iterative density-dependent XC evaluations during SCF. Further validation through infrared spectral predictions, molecular dynamics simulations, and structural perturbation tests demonstrates robust performance and reasonable transferability. This work establishes that machine-learned density-independent mapping represents a practical pathway for designing stable and transferable XC potentials.Keywords
Funding Information
- Advanced Materials-National Science and Technology Major Project (2024ZD0606900)
- National Natural Science Foundation of China (12274171)
- National Natural Science Foundation of China (12674296)
- National Key Research and Development Program of China (2023YFA1406200)
- National Key Research and Development Program of China (2023YFB3003001)
- National Science Foundation (CHE-2154760)
- National Science Foundation (OAC-2321103)
This publication has 41 references indexed in Scilit:
- Real-space machine learning of correlation density functionalsNature Communications, 2025
- Machine learning electronic structure methods based on the one-electron reduced density matrixNature Communications, 2023
- How Well Does Kohn–Sham Regularizer Work for Weakly Correlated Systems?The Journal of Physical Chemistry Letters, 2022
- CIDER: An Expressive, Nonlocal Feature Set for Machine Learning Density Functionals with Exact ConstraintsJournal of Chemical Theory and Computation, 2022
- Pure non-local machine-learned density functional theory for electron correlationNature Communications, 2021
- Accurate and Numerically Efficient r2SCAN Meta-Generalized Gradient ApproximationThe Journal of Physical Chemistry Letters, 2020
- Machine learning accurate exchange and correlation functionals of the electronic densityNature Communications, 2020
- Bypassing the Kohn-Sham equations with machine learningNature Communications, 2017
- PySCF: the Python‐based simulations of chemistry frameworkWIREs Computational Molecular Science, 2017
- Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force FieldsThe Journal of Physical Chemistry, 1994