Autonomous Experiments for Neutron Three-Axis Spectrometers (TAS) with Log-Gaussian Processes

TL;DR

This paper proposes using log-Gaussian processes to enhance autonomous neutron scattering experiments, specifically for three-axis spectrometers, by optimizing experimental resource allocation through active learning.

Contribution

It introduces log-Gaussian processes as a novel approach for autonomous experiments in neutron scattering, improving upon traditional Gaussian process methods.

Findings

Effective autonomous experiment framework demonstrated for TAS with PANDA

Log-Gaussian processes improve uncertainty quantification in neutron experiments

Enhanced efficiency in material discovery through optimized beam time usage

Abstract

Autonomous experiments are excellent tools to increase the efficiency of material discovery. Indeed, AI and ML methods can help optimizing valuable experimental resources as, for example, beam time in neutron scattering experiments, in addition to scientists' knowledge and experience. Active learning methods form a particular class of techniques that acquire knowledge on a specific quantity of interest by autonomous decisions on what or where to investigate next based on previous measurements. For instance, Gaussian Process Regression (GPR) is a well-known technique that can be exploited to accomplish active learning tasks for scattering experiments as was recently demonstrated. Gaussian processes are not only capable to approximate functions by their posterior mean function, but can also quantify uncertainty about the approximation itself. Hence, if we perform function evaluations at locations of highest uncertainty, the function can be "optimally" learned in an iterative manner. We suggest the use of log-Gaussian processes, being a natural approach to successfully conduct autonomous neutron scattering experiments in general and TAS experiments with the instrument PANDA at MLZ in particular.