DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Uncovering obscured phonon dynamics from powder inelastic neutron scattering using machine learning

Journal Article · · Machine Learning: Science and Technology

Abstract The study of phonon dynamics is pivotal for understanding material properties, yet it faces challenges due to the irreversible information loss inherent in powder inelastic neutron scattering spectra and the limitations of traditional analysis methods. In this study, we present a machine learning framework designed to reveal obscured phonon dynamics from powder spectra. Using a variational autoencoder, we obtain a disentangled latent representation of spectra and successfully extract force constants for reconstructing phonon dispersions. Notably, our model demonstrates effective applicability to experimental data even when trained exclusively on physics-based simulations. The fine-tuning with experimental spectra further mitigates issues arising from domain shift. Analysis of latent space underscores the model’s versatility and generalizability, affirming its suitability for complex system applications. Furthermore, our framework’s two-stage design is promising for developing a universal pre-trained feature extractor. This approach has the potential to revolutionize neutron measurements of phonon dynamics, offering researchers a potent tool to decipher intricate spectra and gain valuable insights into the intrinsic physics of materials.

Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
Grant/Contract Number:
SC0023874
OSTI ID:
2447544
Journal Information:
Machine Learning: Science and Technology, Journal Name: Machine Learning: Science and Technology Journal Issue: 3 Vol. 5; ISSN 2632-2153
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (29)

Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position journal April 1980
Spin-phonon interactions induced anomalous thermal conductivity in nickel (II) oxide journal June 2023
Mantid—Data analysis and visualization package for neutron scattering and μ SR experiments
  • Arnold, O.; Bilheux, J. C.; Borreguero, J. M.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 764 https://doi.org/10.1016/j.nima.2014.07.029
journal November 2014
First principles phonon calculations in materials science journal November 2015
Rapid Identification of X-ray Diffraction Patterns Based on Very Limited Data by Interpretable Convolutional Neural Networks journal March 2020
Simulation of Inelastic Neutron Scattering Spectra Using OCLIMAX journal January 2019
Machine-learning-assisted insight into spin ice Dy2Ti2O7 journal February 2020
Direct observation of large electron–phonon interaction effect on phonon heat transport journal November 2020
Capturing dynamical correlations using implicit neural representations journal September 2023
Integration of machine learning with neutron scattering for the Hamiltonian tuning of spin ice under pressure journal November 2022
Using generative adversarial networks to match experimental and simulated inelastic neutron scattering data journal January 2023
Machine learning for analysis of experimental scattering and spectroscopy data in materials chemistry journal January 2023
Design and operation of the wide angular-range chopper spectrometer ARCS at the Spallation Neutron Source journal January 2012
A comparison of four direct geometry time-of-flight spectrometers at the Spallation Neutron Source journal April 2014
Machine learning on neutron and x-ray scattering and spectroscopies journal September 2021
Elucidating proximity magnetism through polarized neutron reflectometry and machine learning journal March 2022
Mutual spin-phonon driving effects and phonon eigenvector renormalization in nickel (II) oxide journal July 2022
Interpretable, calibrated neural networks for analysis and understanding of inelastic neutron scattering data journal April 2021
Machine learning for neutron scattering at ORNL * journal January 2021
A Simplex Method for Function Minimization journal January 1965
X-Ray Study of Lattice Vibrations in Aluminum journal August 1956
Normal Vibrations in Aluminum and Derived Thermodynamic Properties journal March 1966
Phonons in aluminum at high temperatures studied by inelastic neutron scattering journal January 2008
Direct observation of magnon-phonon coupling in yttrium iron garnet journal September 2017
Extraction of interaction parameters for α−RuCl3 from neutron data using machine learning journal June 2022
Automated prediction of lattice parameters from X-ray powder diffraction patterns journal November 2021
Gradient-based learning applied to document recognition journal January 1998
ImageNet classification with deep convolutional neural networks journal May 2017
Dataset: Uncovering Obscured Phonon Dynamics from Powder Inelastic Neutron Scattering using Machine Learning dataset January 2023