Batch Discovery of Complex Metal Superhydrides via an Effective Machine Learning Method Structured by Chemical Template Concept

Metal superhydrides, known for their high hydrogen content and polyhedral hydrogen cages, are promising candidates for high-temperature superconductivity. Despite extensive studies on binary metal superhydrides, there remains a large, unexplored chemical space, particularly regarding noninteger hydrogen-to-metal ratios. By integrating the "chemical template effect" with machine learning algorithms, we developed a specialized structure discovery workflow that significantly enhances the efficiency of predicting stable superhydrides. Within the compiled data set used in this work, our method led to the identification of 13 new structural prototypes and 31 stable metal superhydrides, representing a 23% increase in discoveries. The 3D hydrogen clathrates in these compounds are significantly correlated with high superconducting transition temperatures (<i>T</i>_c), and our approach achieves a remarkable 65% increase. Most of these structures contain over 50 atoms per primitive cell, with the <i>I</i>4/<i>m</i> M₁₀H₈₄ prototype having the largest unit cell, containing 94 atoms. Additionally, 19 of the newly identified superhydrides exhibit <i>T</i>_c > 100 K, highlighting the potential for higher <i>T</i>_c materials within the 3D hydrogen clathrate structures. The method also shows good potential to search for ternary superhydrides on a large scale.