Rapid discovery and synthesis of new materials requires intelligent data acquisition strategies to navigate large design spaces. A popular strategy is Bayesian optimization, which aims to find candidates that maximize material properties; however, materials design often requires finding specific subsets of the design space which meet more complex or specialized goals. We present a framework that captures experimental goals through straightforward user-defined filtering algorithms. These algorithms are automatically translated into one of three intelligent, parameter-free, sequential data acquisition strategies (SwitchBAX, InfoBAX, and MeanBAX). Our framework is tailored for typical discrete search spaces involving multiple measured physical properties and short time-horizon decision making. We evaluate this approach on datasets for TiO2 nanoparticle synthesis and magnetic materials characterization, and show that our methods are significantly more efficient than state-of-the-art approaches.
@article{arxiv.2312.16078,
title = {Targeted materials discovery using Bayesian algorithm execution},
author = {Sathya Chitturi and Akash Ramdas and Yue Wu and Brian Rohr and Stefano Ermon and Jennifer Dionne and Felipe H. da Jornada and Mike Dunne and Christopher Tassone and Willie Neiswanger and Daniel Ratner},
journal= {arXiv preprint arXiv:2312.16078},
year = {2023}
}