Machine learning guided discovery of ternary compounds involving La and immiscible Co and Pb elements

Abstract Ternary compounds with an immiscible pair of elements are relatively unexplored but promising for novel quantum materials discovery. Exploring what third element and its ratio that can be added to make stable ternary out remains a great challenge. In this work, we combine machine learning (ML) method ab initio calculations efficiently search the energetically favorable La-Co-Pb containing Co Pb. Three previously reported structures correctly captured by our approach. Moreover, predict ground state La 3 CoPb compound 57 low-energy compounds. Attempts synthesize via multiple techniques produce mixed or multi-phases samples with, at best, ambiguous signals predicted lowest-energy second 18 28 Pb phases. The calculated results Gibbs free energy consistent experiments, will provide very useful guidance further experimental synthesis.