» Articles » PMID: 39872916

: Active Learning in Neutron Reflectometry for Fast Data Acquisition

Overview
Date 2025 Jan 28
PMID 39872916
Authors
Affiliations
Soon will be listed here.
Abstract

Neutron reflectometry (NR) is a powerful technique for interrogating the structure of thin films at interfaces. Because NR measurements are slow and instrument availability is limited, measurement efficiency is paramount. One approach to improving measurement efficiency is active learning (AL), in which the next measurement configurations are selected on the basis of information gained from the partial data collected so far. , a model-based AL algorithm for neutron reflectometry measurements, is presented in this manuscript. uses the existing measurements of a function to choose both the position and the duration of the next measurement. maximizes the information acquisition rate in specific model parameters of interest and uses the well defined signal-to-noise ratio in counting measurements to choose appropriate measurement times. Since continuous measurement is desirable for practical implementation, features forecasting, in which the optimal positions of multiple future measurements are predicted from existing measurements. The performance of is compared with that of well established best practice measurements for supported lipid bilayer samples using realistic digital twins of monochromatic and polychromatic reflectometers. is shown to improve NR measurement speeds in all cases significantly.

References
1.
Teixeira Parente M, Brandl G, Franz C, Stuhr U, Ganeva M, Schneidewind A . Active learning-assisted neutron spectroscopy with log-Gaussian processes. Nat Commun. 2023; 14(1):2246. PMC: 10115805. DOI: 10.1038/s41467-023-37418-8. View

2.
Hoogerheide D, Heinrich F, Maranville B, Majkrzak C . Accurate background correction in neutron reflectometry studies of soft condensed matter films in contact with fluid reservoirs. J Appl Crystallogr. 2021; 53(1). PMC: 8240731. DOI: 10.1107/s160057671901481x. View

3.
Heinrich F, Kienzle P, Hoogerheide D, Losche M . Information gain from isotopic contrast variation in neutron reflectometry on protein-membrane complex structures. J Appl Crystallogr. 2020; 53(Pt 3):800-810. PMC: 7312142. DOI: 10.1107/S1600576720005634. View

4.
Kusne A, Yu H, Wu C, Zhang H, Hattrick-Simpers J, DeCost B . On-the-fly closed-loop materials discovery via Bayesian active learning. Nat Commun. 2020; 11(1):5966. PMC: 7686338. DOI: 10.1038/s41467-020-19597-w. View

5.
Maliszewskyj N, Osovizky A, Pritchard K, Yehuda-Zada Y, Binkley E, Ziegler J . An energy analyzing detector for cold neutrons. Nucl Instrum Methods Phys Res A. 2024; 907. PMC: 11519971. DOI: 10.1016/j.nima.2018.05.023. View