Evaluating AI-guided Design for Scientific Discovery

Michael Pekala, Elizabeth Ann Pogue, Kyle McElroy, Alexander New, Gregory Bassen, Brandon Wilfong, Janna Domenico, Tyrel McQueen, Christopher D Stiles

Submission Track: Papers

Submission Category: AI-Guided Design

Keywords: machine learning, AI-guided design, superconductivity

TL;DR: We propose a methodology for evaluating the rate of novel discovery in adaptive design settings.

Abstract: Machine learning has great potential to revolutionize experimental materials research; however, the degree to which these approaches accelerate novel discovery is rarely quantified. To this end, we propose a framework for characterizing the rate of “first discovery” of scientific hypotheses in the form of materials families. We use a combination of the SuperCon and Materials Project databases to simulate a scientific needle-in-a-haystack discovery problem as a motivating example. We use this approach to compare the ability of different adaptive sampling strategies to rediscover promising superconductor families, such as the Cuprates and iron-based superconductors. This methodology can be applied using various notions of novelty, making it applicable to discovery problems more broadly.

Submission Number: 37