Hierarchical symbolic regression for identifying key physical parameters correlated with bulk properties of perovskites

Abstract

Symbolic regression identifies key physical parameters describing materials properties by uncovering correlations as nonlinear analytical expressions. However, the pool of expressions grows rapidly with complexity, compromising its efficiency. We tackle this challenge by a hierarchical approach: identified expressions are used as input parameters for obtaining more complex expressions. Crucially, this framework can transfer knowledge among properties, highlighting physical relationships. We demonstrate this strategy by using the Sure-Independence-Screening-and-Sparsifying-Operator (SISSO) approach to identify expressions correlated with the lattice constant and cohesive energy, which are then used to model the bulk modulus of ABO3 perovskites.

References in corpus (4)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Big Data of Materials Science - Critical Role of the Descriptor
• Compressive sensing as a new paradigm for model building
• Screened hybrid functional applied to 3d^0-->3d^8 transition-metal perovskites LaMO3 (M=Sc-Cu): influence of the exchange mixing parameter on the structural, electronic and magnetic properties