Stable and accurate orbital-free density functional theory powered by machine learning
Hohenberg and Kohn have proven that the electronic energy and the one-particle electron density can, in principle, be obtained by minimizing an energy functional with respect to the density. While decades of theoretical work have produced increasingly faithful approximations to this elusive exact en...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
August 1, 2025
|
| In: |
Journal of the American Chemical Society
Year: 2025, Volume: 147, Issue: 32, Pages: 28851-28859 |
| ISSN: | 1520-5126 |
| DOI: | 10.1021/jacs.5c06219 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1021/jacs.5c06219 Verlag, kostenfrei, Volltext: https://pubs.acs.org/doi/10.1021/jacs.5c06219 
|
| Author Notes: | Roman Remme, Tobias Kaczun, Tim Ebert, Christof A. Gehrig, Dominik Geng, Gerrit Gerhartz, Marc K. Ickler, Manuel V. Klockow, Peter Lippmann, Johannes S. Schmidt, Simon Wagner, Andreas Dreuw, and Fred A. Hamprecht |
| Summary: | Hohenberg and Kohn have proven that the electronic energy and the one-particle electron density can, in principle, be obtained by minimizing an energy functional with respect to the density. While decades of theoretical work have produced increasingly faithful approximations to this elusive exact energy functional, their accuracy is still insufficient for many applications, making it reasonable to try and learn it empirically. Using rotationally equivariant atomistic machine learning, we obtain for the first time a density functional that, when applied to the organic molecules in QM9, yields energies with chemical accuracy relative to the Kohn-Sham reference while also converging to meaningful electron densities. Augmenting the training data with densities obtained from perturbed potentials proved key to these advances. This work demonstrates that machine learning can play a crucial role in narrowing the gap between theory and the practical realization of Hohenberg and Kohn’s vision, paving the way for more efficient calculations in large molecular systems. The trained STRUCTURES25 model is made available along with full source code and data for training and inference. |
|---|---|
| Item Description: | Gesehen am 24.11.2025 |
| Physical Description: | Online Resource |
| ISSN: | 1520-5126 |
| DOI: | 10.1021/jacs.5c06219 |