A thermodynamic correction layer for machine learning interatomic potentials
Abstract
Machine learning interatomic potentials enable atomistic simulations with near \textit{ab initio} accuracy over large length and time scales. Foundation models extend this capability across the periodic table but inherit the thermodynamic description of the electronic structure methods used to generate their training data. Small errors in relative phase stability can therefore produce large errors in transformation temperatures. We introduce an additive thermodynamic correction layer that shifts phase free energies towards an assessed reference without retraining or modifying the base potential. A first order thermodynamic construction converts the required phase free energy shifts directly into configuration energy targets, which are fitted using a linear atomic cluster expansion and refined iteratively from measured free energies. We apply the method to melting and solid to solid transformations across elements with different crystal structures using a foundation GRACE model. After the correction, all transformation temperatures lie within the prescribed tolerance of the assessed values, including Ca, Ti, and Zr, where a solid to solid transition and melting are corrected together. Static energy curves, bulk moduli, and liquid structure remain close to those of the base model. Vacancy formation energies, thermal expansion, and liquid density depend on the corrected phase balance and change where the correction is large. The method requires neither retraining, differentiable dynamics, nor access to the parameters of the base potential. It provides a modular route for combining transferable atomistic models with assessed phase thermodynamics.
Related
- Benchmarking machine-learning interatomic potentials using classical force fields
- MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
- Cluster-based Structural Similarity for Dataset Visualization and Data Selection for Machine Learning Interatomic Potentials
- Leveraging Machine Learning Interatomic Potentials into Fitting Fast and Accurate AMBER-Compatible Precise Force Field
- Truncated automatic sparse differentiation for machine learning interatomic potentials
BibTeX
@misc{menon2026thermodynamic,
title = {{A thermodynamic correction layer for machine learning interatomic potentials}},
author = {Sarath Menon and Braulio Sanchez Ortega and Ralf Drautz},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.34551},
eprint = {2610.34551},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.34551},
}
RIS
TY - UNPB
TI - A thermodynamic correction layer for machine learning interatomic potentials
AU - Sarath Menon
AU - Braulio Sanchez Ortega
AU - Ralf Drautz
PY - 2026
DA - 2026/10/25
PB - arXiv
DO - 10.48550/arxiv.2610.34551
UR - https://arxiv.org/abs/2610.34551
AB - Machine learning interatomic potentials enable atomistic simulations with near \textit{ab initio} accuracy over large length and time scales. Foundation models extend this capability across the periodic table but inherit the thermodynamic description of the electronic structure methods used to generate their training data. Small errors in relative phase stability can therefore produce large errors in transformation temperatures. We introduce an additive thermodynamic correction layer that shifts phase free energies towards an assessed reference without retraining or modifying the base potential. A first order thermodynamic construction converts the required phase free energy shifts directly into configuration energy targets, which are fitted using a linear atomic cluster expansion and refined iteratively from measured free energies. We apply the method to melting and solid to solid transformations across elements with different crystal structures using a foundation GRACE model. After the correction, all transformation temperatures lie within the prescribed tolerance of the assessed values, including Ca, Ti, and Zr, where a solid to solid transition and melting are corrected together. Static energy curves, bulk moduli, and liquid structure remain close to those of the base model. Vacancy formation energies, thermal expansion, and liquid density depend on the corrected phase balance and change where the correction is large. The method requires neither retraining, differentiable dynamics, nor access to the parameters of the base potential. It provides a modular route for combining transferable atomistic models with assessed phase thermodynamics.
ER -