Journal Article

Targeted materials discovery using Bayesian algorithm execution

Ramdas, Akash, Neiswanger, Willie, Dunne, Mike, Wu, Yue, Dionne, Jennifer, Ermon, Stefano, Chitturi, Sathya R., Rohr, Brian, Tassone, Christopher, Jornada, Felipe H. da, Ratner, Daniel

2024

Overview

Rapid discovery and synthesis of future 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 collection strategies (SwitchBAX, InfoBAX, and MeanBAX), bypassing the time-consuming and difficult process of task-specific acquisition function design. Our framework is tailored for typical discrete search spaces involving multiple measured physical properties and short time-horizon decision making. We demonstrate this approach on datasets for TiO 2 nanoparticle synthesis and magnetic materials characterization, and show that our methods are significantly more efficient than state-of-the-art approaches. Overall, our framework provides a practical solution for navigating the complexities of materials design, and helps lay groundwork for the accelerated development of advanced materials.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 639/301/1034/1037 / 639/301/930/1032 / Active Learning / Algorithms / Autonomous Experiments / Bayesian analysis / Bayesian Optimization / Characterization and Evaluation of Materials / Chemistry and Materials Science / Computational Intelligence / Data acquisition / Data collection / Decision making / Design of Experiments / Design optimization / ENGINEERING / Machine Learning / Magnetic materials / Magnetic properties / Material properties / Materials Discovery / Materials Science / Mathematical and Computational Engineering / Mathematical and Computational Physics / Mathematical Modeling and Industrial Mathematics / MATHEMATICS AND COMPUTING / Mental task performance / Nanoparticles / Physical properties / Synthesis / Target acquisition / Theoretical / Time measurement / Titanium dioxide