AI Can Predict, but Experiments Must Test: A New Role for Neutron Facilities in a Materials AI World.
- 1ISIS Neutron and Muon Source, Rutherford Appleton Laboratory, Harwell Campus, DidcotOX11 0QX, United Kingdom.
- 2Department of Chemistry, University of Bath, BathBA2 7AY, United Kingdom.
Abstract
Materials AI is advancing at an exceptional pace and attracting growing investment, while the experimental scientific facilities and people needed to test and improve its predictions face mounting pressure. Unlike increasingly standardized data-center builds, neutron facilities are bespoke, source- and instrument-specific capabilities that take many years to build and mature, making lost capacity exceptionally difficult to replace. The response should be to embrace this shift by aligning experimental capability with the problems AI is increasingly being used to solve. For atomistic materials modeling, machine-learned interatomic potentials (MLIPs) provide a natural focus, and we propose coordinated experimental validation at two scales. Workhorse campaigns would combine automated room-temperature diffraction and low-temperature inelastic neutron scattering across reusable libraries of hundreds of well-characterized samples, with observables predicted before beamtime and compared systematically with experiment. Targeted parametric studies would examine selected systems across temperature, pressure, adsorption and guest loading using quasielastic neutron scattering, total scattering and complementary diffraction and spectroscopy. Together, these measurements would expose broad performance trends and physical origins of failure, while separating development, diagnostic and blind challenge data for subsequent model improvement. Neutron facilities are not alternatives to AI investment; they are experimental infrastructure through which atomistic materials AI can be tested against reality.
Related
- Assessment of Pleurotus ostreatus and Pleurotus citrinopileatus mushroom as bioshielding materials for neutron attenuation in medical cyclotron
- Evaluation of airborne PFAS concentrations in PFAS-using industrial facilities
- Impact of Shared Facilities in Advancing Solid-State NMR Research: 2025 Edition
- Enhanced Azo Dye Removal via Alginate-Immobilized Ganoderma lucidum: From Batch Experiments to Continuous Column Studies
- Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments
BibTeX
@article{armstrong2026predict,
title = {{AI Can Predict, but Experiments Must Test: A New Role for Neutron Facilities in a Materials AI World.}},
author = {Jeff Armstrong},
journal = {The journal of physical chemistry letters},
year = {2026},
month = sep,
doi = {10.1021/acs.jpclett.6c02724},
url = {https://europepmc.org/article/MED/42917878},
note = {CC BY},
}
RIS
TY - JOUR
TI - AI Can Predict, but Experiments Must Test: A New Role for Neutron Facilities in a Materials AI World.
AU - Jeff Armstrong
PY - 2026
DA - 2026/09/01
JO - The journal of physical chemistry letters
DO - 10.1021/acs.jpclett.6c02724
UR - https://europepmc.org/article/MED/42917878
AB - Materials AI is advancing at an exceptional pace and attracting growing investment, while the experimental scientific facilities and people needed to test and improve its predictions face mounting pressure. Unlike increasingly standardized data-center builds, neutron facilities are bespoke, source- and instrument-specific capabilities that take many years to build and mature, making lost capacity exceptionally difficult to replace. The response should be to embrace this shift by aligning experimental capability with the problems AI is increasingly being used to solve. For atomistic materials modeling, machine-learned interatomic potentials (MLIPs) provide a natural focus, and we propose coordinated experimental validation at two scales. Workhorse campaigns would combine automated room-temperature diffraction and low-temperature inelastic neutron scattering across reusable libraries of hundreds of well-characterized samples, with observables predicted before beamtime and compared systematically with experiment. Targeted parametric studies would examine selected systems across temperature, pressure, adsorption and guest loading using quasielastic neutron scattering, total scattering and complementary diffraction and spectroscopy. Together, these measurements would expose broad performance trends and physical origins of failure, while separating development, diagnostic and blind challenge data for subsequent model improvement. Neutron facilities are not alternatives to AI investment; they are experimental infrastructure through which atomistic materials AI can be tested against reality.
SN - 1948-7185
ER -