Integration of Machine Learning with Neutron Scattering: Hamiltonian Tuning in Spin Ice with Pressure

TL;DR

This paper presents an integrated machine learning framework that enhances neutron scattering experiments by enabling rapid data analysis, parameter extraction, and phase diagram construction in complex quantum materials like spin ice under pressure.

Contribution

It introduces a novel scheme combining neural autoencoders and generative models to streamline theory-experiment co-design in neutron scattering studies of frustrated magnets.

Findings

Successfully guided neutron experiments on Dy₂Ti₂O₇ using ML predictions

Enabled rapid extraction of material parameters and phase diagram construction

Demonstrated integration of ML with high-performance simulations and measurements

Abstract

Quantum materials research requires co-design of theory with experiments and involves demanding simulations and the analysis of vast quantities of data, usually including pattern recognition and clustering. Artificial intelligence is a natural route to optimise these processes and bring theory and experiments together. Here we propose a scheme that integrates machine learning with high-performance simulations and scattering measurements, covering the pipeline of typical neutron experiments. Our approach uses nonlinear autoencoders trained on realistic simulations along with a fast surrogate for the calculation of scattering in the form of a generative model. We demonstrate this approach in a highly frustrated magnet, Dy$_2$Ti$_2$O$_7$, using machine learning predictions to guide the neutron scattering experiment under hydrostatic pressure, extract material parameters and construct a phase diagram. Our scheme provides a comprehensive set of capabilities that allows direct integration of theory along with automated data processing and provides on a rapid timescale direct insight into a challenging condensed matter system.