A Synthesizability-Guided Pipeline for Materials Discovery

Thorben Prein, Willis O'Leary, Aikaterini Flessa Savvidou, Elchaïma Bourneix, Joonatan E. M. Laulainen

Keywords: materials science, machine learning, synthesizability, solid-state synthesis

TL;DR: New synthesizability metric leads to 7/16 successful synthesis of predicted structures in 3 days; model combines composition + structure, countering DFT’s 0 K bias + screening MP, GNoME, Alexandria, exposing database gaps

Abstract: Computational materials discovery relies on the generation of plausible crystal structures. The plausibility is typically judged through density functional theory methods which, while typically accurate at zero Kelvin, often favor low-energy structures that are not experimentally accessible. We develop a combined compositional and structural synthesizability score which provides an accurate way of predicting which compounds can actually be synthesized in a laboratory. We use it to evaluate non-synthesized structures from the Materials Project, GNoME, and Alexandria, and identified several hundred highly synthesizable candidates. We then predict synthesis pathways, conduct corresponding experiments, and characterize the products across 16 targets, \textbf{successfully synthesizing 7 of 16}. The entire experimental process was completed in only three days. Our results highlight omissions in lists of known synthesized structures, deliver insights into the practical utility of current materials databases, and showcase the central role synthesizability prediction can play in materials discovery.

Submission Track: Paper Track (Full Paper)

Submission Category: AI-Guided Design + Automated Synthesis

Institution Location: {Paris, France}, {Munich, Germany}

Submission Number: 113