Capturing dynamical correlations using implicit neural representations.
Sathya R ChitturiZhurun JiAlexander N PetschCheng PengZhantao ChenRajan PlumleyMike DunneSougata MardanyaSugata ChowdhuryHongwei ChenArun BansilAdrian FeiguinAlexander I KolesnikovDharmalingam PrabhakaranStephen M HaydenDaniel RatnerChunjing JiaYoussef NashedJoshua J TurnerPublished in: Nature communications (2023)
Understanding the nature and origin of collective excitations in materials is of fundamental importance for unraveling the underlying physics of a many-body system. Excitation spectra are usually obtained by measuring the dynamical structure factor, S(Q, ω), using inelastic neutron or x-ray scattering techniques and are analyzed by comparing the experimental results against calculated predictions. We introduce a data-driven analysis tool which leverages 'neural implicit representations' that are specifically tailored for handling spectrographic measurements and are able to efficiently obtain unknown parameters from experimental data via automatic differentiation. In this work, we employ linear spin wave theory simulations to train a machine learning platform, enabling precise exchange parameter extraction from inelastic neutron scattering data on the square-lattice spin-1 antiferromagnet La 2 NiO 4 , showcasing a viable pathway towards automatic refinement of advanced models for ordered magnetic systems.
Keyphrases
- density functional theory
- machine learning
- molecular dynamics
- big data
- deep learning
- working memory
- electronic health record
- room temperature
- artificial intelligence
- monte carlo
- high resolution
- high throughput
- neural network
- computed tomography
- molecularly imprinted
- data analysis
- smoking cessation
- high speed
- magnetic resonance imaging
- dual energy
- electron microscopy