An Effective Machine Learning Frame for Materials Discovery Structured by a Chemical Concept

Yuanhui Sun, Austin Ellis, xin chen, Maosheng Miao

Keywords: Stack-emsembling ML, crystal structure search, chemical template, metal superhydrides

TL;DR: We developed a machine-learning–guided chemical template workflow that uncovered 13 new prototypes and 31 stable metal superhydrides, including 19 with 𝑇 𝑐 >100 K, greatly expanding the unexplored structural space for high-Tc superconductors.

Abstract: Despite extensive studies on binary compounds with high non-metal compositions, there remains a large, unexplored chemical space, particularly regarding non-integer non-metal-to-metal ratios. By integrating the chemical template concept with machine learning algorithms, we developed a specialized structure discovery workflow that significantly enhances the efficiency of predicting stable compounds. Our method led to the identification of 13 new structural prototypes and 31 stable metal superhydrides, representing a 23% increase in discoveries. Metal superhydrides, known for their high hydrogen content and polyhedral hydrogen cages, are promising candidates for high-temperature superconductivity. The method enables us to discover many structures containing over 50 atoms per primitive cell. Additionally, 19 of the newly identified superhydrides exhibit Tc > 100 K, highlighting the potential for higher Tc materials within the 3D hydrogen clathrate structures.

Submission Track: Paper Track (Short Paper)

Submission Category: AI-Guided Design

Institution Location: (Los Angeles, USA)

Submission Number: 77