Approaching the Inverse Neutron Scattering Problem with Neural Networks

Abstract

Determining the microscopic Hamiltonian of a quantum magnet from inelastic neutron scattering measurements remains a central challenge in condensed matter physics. While the dynamical spin structure factor contains, in principle, sufficient information about the underlying interactions, extracting Hamiltonian parameters from experimental spectra constitutes a highly nontrivial inverse problem due to the large parameter space and the presence of experimental noise. Here we demonstrate that neural networks can efficiently solve this inverse problem for a broad class of quantum magnets. As a benchmark, we consider an eight-parameter family of honeycomb lattice Heisenberg spin models in the fully polarized phase, where the dynamical spin structure factor can be computed exactly within linear spin-wave theory. Using a large synthetic dataset of neutron scattering spectra, we train neural networks to infer the underlying Hamiltonian parameters directly from the dynamical response. We compare the performance of three different architectures---fully connected neural networks (FCNNs), one-dimensional convolutional neural networks (CNN1Ds), and two-dimensional convolutional neural networks (CNN2Ds)---and find that all achieve high predictive accuracy. Remarkably, the trained models remain robust in the presence of substantial experimental uncertainty, reliably recovering the Hamiltonian parameters even when the input spectra are contaminated by random noise with amplitudes reaching 10% of the signal intensity. Our results establish machine learning as a powerful framework for quantitative Hamiltonian reconstruction from neutron scattering data and provide a practical route toward automated characterization of quantum magnetic materials.

Compositional neural networks for multimodal X-ray and neutron scattering inversion
Valentin Munteanu, Alexander Hinderhofer, Dmitry Lapkin +2
arXiv21 Oct 2026PreprintCC BY 4.0Full textApplied physics & instrumentation Condensed matterarXiv
Non-uniqueness of the amplitude reconstruction in the inverse scattering problem and a refinement of Hoehler's resonance clustering
A. Švarc
arXiv3 Nov 2026PreprintCC BY 4.0Full textNuclear physicsarXiv
Regularity of core coupled high-spin structure in neutron-rich ^196−202Au isotopes approaching N =126
Y. Cho, Y. H. Kim, A. Navin +49
arXiv2 Nov 2026PreprintCC BY 4.0Full textNuclear physicsarXiv
Evolution of high-spin states in neutron-rich Au195–202 isotopes approaching the N=126 shell closure
Y Cho, Y.H Kim, A Navin +49
Phys.Rev.C23 Sep 2026Peer-reviewedCC BY 4.0Full textNuclear physicsHALarXiv
Reduced vortex descriptors linking polycrystallinity in magnetic nanoparticles with polarized magnetic small-angle neutron scattering
Michael P. Adams, Jonathan Leliaert, Andreas Michels +1
Physical Review Research23 Oct 2026Peer-reviewedPublisher termsAtomic, molecular & optical physicsCrossrefAPS

Cite

BibTeX RIS

BibTeX

@misc{luo2026approaching,
  title = {{Approaching the Inverse Neutron Scattering Problem with Neural Networks}},
  author = {Jingyi Luo and Fletcher Williams and Ang-Kun Wu and David Dahlbom and Cristian D. Batista and Hao Zhang},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.22535},
  eprint = {2609.22535},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.22535},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Approaching the Inverse Neutron Scattering Problem with Neural Networks
AU  - Jingyi Luo
AU  - Fletcher Williams
AU  - Ang-Kun Wu
AU  - David Dahlbom
AU  - Cristian D. Batista
AU  - Hao Zhang
PY  - 2026
DA  - 2026/09/18
PB  - arXiv
DO  - 10.48550/arxiv.2609.22535
UR  - https://arxiv.org/abs/2609.22535
AB  - Determining the microscopic Hamiltonian of a quantum magnet from inelastic neutron scattering measurements remains a central challenge in condensed matter physics. While the dynamical spin structure factor contains, in principle, sufficient information about the underlying interactions, extracting Hamiltonian parameters from experimental spectra constitutes a highly nontrivial inverse problem due to the large parameter space and the presence of experimental noise. Here we demonstrate that neural networks can efficiently solve this inverse problem for a broad class of quantum magnets. As a benchmark, we consider an eight-parameter family of honeycomb lattice Heisenberg spin models in the fully polarized phase, where the dynamical spin structure factor can be computed exactly within linear spin-wave theory. Using a large synthetic dataset of neutron scattering spectra, we train neural networks to infer the underlying Hamiltonian parameters directly from the dynamical response. We compare the performance of three different architectures---fully connected neural networks (FCNNs), one-dimensional convolutional neural networks (CNN1Ds), and two-dimensional convolutional neural networks (CNN2Ds)---and find that all achieve high predictive accuracy. Remarkably, the trained models remain robust in the presence of substantial experimental uncertainty, reliably recovering the Hamiltonian parameters even when the input spectra are contaminated by random noise with amplitudes reaching 10% of the signal intensity. Our results establish machine learning as a powerful framework for quantitative Hamiltonian reconstruction from neutron scattering data and provide a practical route toward automated characterization of quantum magnetic materials.
ER  -

Abstract

Related

Cite