From sparse quantum-computing data to atomistic simulation with universal machine-learning interatomic potentials
Abstract
We propose a framework for incorporating quantum-computing-based electronic-structure calculations into universal machine-learning interatomic potentials (uMLIPs). Rather than constructing an interatomic potential from scratch, we refine a pretrained DFT-based uMLIP using a small set of accurate reference energies obtained from quantum computing. We demonstrate the approach for three chemically distinct applications: the Menshutkin reaction, water adsorption in the metal-organic framework HKUST-1, and CO hopping on a high-entropy-alloy nanoparticle. For the Menshutkin reaction, fine-tuning on gas-phase configurations improves the transition-state energy inside a carbon nanotube but not the product energy. For water adsorption in HKUST-1, fine-tuning with only 14 reference configurations brings adsorption thermodynamics obtained from millions of configurations sampled by Widom insertion into closer agreement with reference values. For CO hopping on an IrPdPtRhRu nanoparticle, the preference for on-top over bridge adsorption is recovered in the finite-temperature free-energy profile obtained from enhanced-sampling molecular dynamics, even though the reference data contain only energies. These results demonstrate that the proposed framework provides a practical route for incorporating quantum-computing calculations into realistic atomistic simulations and that quantum-computing reference data can improve pretrained uMLIPs.
Related
- Correcting the Liquid Densities of Universal Machine-Learning Interatomic Potentials Using Local-Number-Density Repulsion
- Applicability Domain of Universal Machine Learning Interatomic Potentials at Solid-State Battery Interfaces
- Reference Conventions and Structure Types, Rather Than 4f Occupancy, Shape Lanthanide Errors in Universal Machine-Learning Interatomic Potentials
- Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
- Bias in Universal Machine-Learned Interatomic Potentials and Its Effects on Fine-Tuning
BibTeX
@misc{do2026from,
title = {{From sparse quantum-computing data to atomistic simulation with universal machine-learning interatomic potentials}},
author = {Tuan Minh Do and Yuichiro Yoshida and Kenji Ishihara and Wataru Mizukami},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21536},
eprint = {2609.21536},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21536},
}
RIS
TY - UNPB
TI - From sparse quantum-computing data to atomistic simulation with universal machine-learning interatomic potentials
AU - Tuan Minh Do
AU - Yuichiro Yoshida
AU - Kenji Ishihara
AU - Wataru Mizukami
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.21536
UR - https://arxiv.org/abs/2609.21536
AB - We propose a framework for incorporating quantum-computing-based electronic-structure calculations into universal machine-learning interatomic potentials (uMLIPs). Rather than constructing an interatomic potential from scratch, we refine a pretrained DFT-based uMLIP using a small set of accurate reference energies obtained from quantum computing. We demonstrate the approach for three chemically distinct applications: the Menshutkin reaction, water adsorption in the metal-organic framework HKUST-1, and CO hopping on a high-entropy-alloy nanoparticle. For the Menshutkin reaction, fine-tuning on gas-phase configurations improves the transition-state energy inside a carbon nanotube but not the product energy. For water adsorption in HKUST-1, fine-tuning with only 14 reference configurations brings adsorption thermodynamics obtained from millions of configurations sampled by Widom insertion into closer agreement with reference values. For CO hopping on an IrPdPtRhRu nanoparticle, the preference for on-top over bridge adsorption is recovered in the finite-temperature free-energy profile obtained from enhanced-sampling molecular dynamics, even though the reference data contain only energies. These results demonstrate that the proposed framework provides a practical route for incorporating quantum-computing calculations into realistic atomistic simulations and that quantum-computing reference data can improve pretrained uMLIPs.
ER -