Machine learning modeling of materials with a group-subgroup structure

Abstract Crystal structures connected by continuous phase transitions are linked through mathematical relations between crystallographic groups and their subgroups. In the present study, we introduce group-subgroup machine learning (GS-ML) show that including materials with small unit cells in training set decreases out-of-sample prediction errors for large cells. GS-ML incurs least cost to reach 2%–3% target accuracy compared other ML approaches. Since available datasets heterogeneous providing insufficient examples realizing structure, ‘FriezeRMQ1D’ dataset 8393 Q1D organometallic uniformly distributed across seven frieze groups. Furthermore, comparing performances of FCHL 1-hot representations, capture subgroup information efficiently when descriptor encodes structural information. The proposed approach is generic extendable symmetry abstractions such as spin-, valency-, or charge order.