Multimodal characterization is commonly required for understanding materials. User facilities possess the infrastructure to perform these measurements, albeit in serial over days to months. In this paper, we describe a unified multimodal measurement of a single sample library at distant instruments, driven by a concert of distributed agents that use analysis from each modality to inform the direction of the other in real time. Powered by the Bluesky project at the National Synchrotron Light Source II, this experiment is a world's first for beamline science, and provides a blueprint for future approaches to multimodal and multifidelity experiments at user facilities.
Cite
@article{arxiv.2301.09177,
title = {Self-driving Multimodal Studies at User Facilities},
author = {Phillip M. Maffettone and Daniel B. Allan and Stuart I. Campbell and Matthew R. Carbone and Thomas A. Caswell and Brian L. DeCost and Dmitri Gavrilov and Marcus D. Hanwell and Howie Joress and Joshua Lynch and Bruce Ravel and Stuart B. Wilkins and Jakub Wlodek and Daniel Olds},
journal= {arXiv preprint arXiv:2301.09177},
year = {2023}
}
Comments
36th Conference on Neural Information Processing Systems (NeurIPS 2022). AI4Mat Workshop