Capturing dynamical correlations using implicit neural representations

Journal article

The observation and description of collective excitations in solids is a fundamental issue when seeking to understand the physics of a many-body system. Analysis of these excitations is usually carried out by measuring the dynamical structure factor, S(Q, $\omega$), with inelastic neutron or x-ray scattering techniques and comparing this against a calculated dynamical model. Here, we develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. We benchmark this approach on a Linear Spin Wave Theory (LSWT) simulator and advanced inelastic neutron scattering data from the square-lattice spin-1 antiferromagnet La$_2$NiO$_4$. We find that the model predicts the unknown parameters with excellent agreement relative to analytical fitting. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data, without the need for human-guided peak finding and fitting algorithms. This prototypical approach promises a new technology for this field to automatically detect and refine more advanced models for ordered quantum systems.Comment: 12 pages, 7 figure

Authors: Chitturi, SR; Ji, Z; Petsch, AN; Peng, C; Chen, Z

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Nature Research
• Journal: Nature Communications
• Volume: 14
• Issue: 1
• Pages: 5852-5852
• Article number: 5852
• Publication date: 2023-09-20
• DOI: 10.1038/s41467-023-41378-4
• EISSN: 2041-1723
• ISSN: 2041-1723
• Language: English
• Keywords: Computer science; Physics; Artificial intelligence; Statistical physics