Subtle Energy Corrections Reshape Condensed-Phase Property Predictions from a Machine-Learning Interatomic Potential
Abstract
Accurate reproduction of electronic-structure labels by machine-learning interatomic potentials does not necessarily ensure reliable condensed-phase properties. We investigate the effects of basis-set superposition error (BSSE) and an explicit Axilrod-Teller-Muto (ATM) three-body dispersion contribution on molecular-liquid predictions. Starting from MACELES-OFF, we fine-tune a baseline potential at the ωB97M-V/def2-TZVPD level. A separate branch learns counterpoise (CP) energy and force corrections with the baseline frozen, while a D4-parametrized ATM term is added during molecular-dynamics inference. Mean atom-normalized CP and ATM contributions are 0.222 and 0.205 meV/atom, respectively, for the analyzed SPICE2 configurations from OMol25. We compare baseline, CP-only, ATM-only, and CP + ATM variants for 39 organic liquids. Relative to baseline, the mean system-wise density changes are -1.17%, -10.38%, and -11.93% for CP-only, ATM-only, and CP + ATM, respectively; the corresponding enthalpy-of-vaporization changes are -2.79%, -14.74%, and -18.32%. For the 11 liquids with experimental self-diffusion data, the mean self-diffusion changes are +17.66%, +203.02%, and +230.36%. Both corrections thus lower density and enthalpy of vaporization while increasing molecular mobility on average. ATM dominates these changes, while CP provides a smaller contribution; their combination yields the largest average shifts. These results show that corrections with sub-meV/atom mean values on the analyzed configurations can substantially reshape the predicted structural, thermodynamic, and transport properties of molecular liquids.
Related
- Transfer learning on universal interatomic potential embeddings improves generalization in structure-property defect models
- A Divide-and-Conquer Embedded Correlated Wavefunction Transfer Learning Approach for Chemically Accurate Condensed-Phase Interatomic Potentials: Liquid Water as a Test Case.
- Embedded Morgan Fingerprints for more efficient molecular property predictions with machine learning
- Accuracy, Reliability, and Efficiency of a MACE Machine-Learning Interatomic Potential for Aspirin: A Reproducible Benchmark for Molecular Simulation
- Quantum-Classical Effective Fragment Potential Embedding for Condensed-Phase Quantum Chemistry
BibTeX
@misc{wang2026subtle,
title = {{Subtle Energy Corrections Reshape Condensed-Phase Property Predictions from a Machine-Learning Interatomic Potential}},
author = {Haihui Wang and Xinyan Wang and Jiashu Liang and Yuanheng Wang and Chang Han and Wen Yan and Tianze Zheng and Kuang Yu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.06109},
eprint = {2611.06109},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.06109},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Subtle Energy Corrections Reshape Condensed-Phase Property Predictions from a Machine-Learning Interatomic Potential
AU - Haihui Wang
AU - Xinyan Wang
AU - Jiashu Liang
AU - Yuanheng Wang
AU - Chang Han
AU - Wen Yan
AU - Tianze Zheng
AU - Kuang Yu
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.06109
UR - https://arxiv.org/abs/2611.06109
AB - Accurate reproduction of electronic-structure labels by machine-learning interatomic potentials does not necessarily ensure reliable condensed-phase properties. We investigate the effects of basis-set superposition error (BSSE) and an explicit Axilrod-Teller-Muto (ATM) three-body dispersion contribution on molecular-liquid predictions. Starting from MACELES-OFF, we fine-tune a baseline potential at the ωB97M-V/def2-TZVPD level. A separate branch learns counterpoise (CP) energy and force corrections with the baseline frozen, while a D4-parametrized ATM term is added during molecular-dynamics inference. Mean atom-normalized CP and ATM contributions are 0.222 and 0.205 meV/atom, respectively, for the analyzed SPICE2 configurations from OMol25. We compare baseline, CP-only, ATM-only, and CP + ATM variants for 39 organic liquids. Relative to baseline, the mean system-wise density changes are -1.17%, -10.38%, and -11.93% for CP-only, ATM-only, and CP + ATM, respectively; the corresponding enthalpy-of-vaporization changes are -2.79%, -14.74%, and -18.32%. For the 11 liquids with experimental self-diffusion data, the mean self-diffusion changes are +17.66%, +203.02%, and +230.36%. Both corrections thus lower density and enthalpy of vaporization while increasing molecular mobility on average. ATM dominates these changes, while CP provides a smaller contribution; their combination yields the largest average shifts. These results show that corrections with sub-meV/atom mean values on the analyzed configurations can substantially reshape the predicted structural, thermodynamic, and transport properties of molecular liquids.
ER -