Research

Paper

TESTING March 05, 2026

High-Pressure Inelastic Neutron Spectroscopy: A true test of Machine-Learned Interatomic Potential energy landscapes

Authors

Jeff Armstrong, Adam Jackson, Alin Elena

Abstract

Machine-learned interatomic potentials (MLIPs) promise to provide near density-functional theory accuracy at a fraction of the computational cost, offering a transformative route toward genuinely predictive chemistry. Yet their predictive validity beyond the training regime remains largely untested experimentally. Here we use pressure-dependent broadband inelastic neutron spectroscopy (INS) as a direct experimental probe of MLIP transferability. Employing a newly developed high-pressure superalloy clamp cell, we measure INS spectra of crystalline 2,5-diiodothiophene at 10~K under ambient conditions and at 1.5~GPa. A MACE-based MLIP, fine-tuned on targeted DFT data, reproduces the experimental spectra across 0--1200~cm$^{-1}$ at both pressures and remains thermodynamically stable under rigorous molecular dynamics validation at 300~K. The model captures systematic pressure-induced blue shifts arising from steric stiffening and reproduces an anomalous red shift at 453~cm$^{-1}$ driven by pressure-modified intermolecular interactions, providing direct validation of its many-body character. This constitutes the first experimental demonstration of MLIP transferability across distinct thermodynamic states using neutron spectroscopy, and establishes high-pressure INS as a stringent benchmark for predictive machine-learned potentials.

Metadata

arXiv ID: 2603.05442
Provider: ARXIV
Primary Category: cond-mat.mtrl-sci
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05442v1</id>\n    <title>High-Pressure Inelastic Neutron Spectroscopy: A true test of Machine-Learned Interatomic Potential energy landscapes</title>\n    <updated>2026-03-05T18:03:29Z</updated>\n    <link href='https://arxiv.org/abs/2603.05442v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05442v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Machine-learned interatomic potentials (MLIPs) promise to provide near density-functional theory accuracy at a fraction of the computational cost, offering a transformative route toward genuinely predictive chemistry. Yet their predictive validity beyond the training regime remains largely untested experimentally.\n  Here we use pressure-dependent broadband inelastic neutron spectroscopy (INS) as a direct experimental probe of MLIP transferability. Employing a newly developed high-pressure superalloy clamp cell, we measure INS spectra of crystalline 2,5-diiodothiophene at 10~K under ambient conditions and at 1.5~GPa. A MACE-based MLIP, fine-tuned on targeted DFT data, reproduces the experimental spectra across 0--1200~cm$^{-1}$ at both pressures and remains thermodynamically stable under rigorous molecular dynamics validation at 300~K. The model captures systematic pressure-induced blue shifts arising from steric stiffening and reproduces an anomalous red shift at 453~cm$^{-1}$ driven by pressure-modified intermolecular interactions, providing direct validation of its many-body character.\n  This constitutes the first experimental demonstration of MLIP transferability across distinct thermodynamic states using neutron spectroscopy, and establishes high-pressure INS as a stringent benchmark for predictive machine-learned potentials.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cond-mat.mtrl-sci'/>\n    <published>2026-03-05T18:03:29Z</published>\n    <arxiv:primary_category term='cond-mat.mtrl-sci'/>\n    <author>\n      <name>Jeff Armstrong</name>\n    </author>\n    <author>\n      <name>Adam Jackson</name>\n    </author>\n    <author>\n      <name>Alin Elena</name>\n    </author>\n  </entry>"
}