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

TL;DR

This paper introduces a hierarchical symbolic regression method that efficiently uncovers key physical parameters and their relationships with bulk properties of perovskites, enabling transfer of knowledge among different material properties.

Contribution

It presents a hierarchical framework for symbolic regression that improves efficiency and reveals physical relationships by reusing expressions across properties.

Findings

Successfully identified expressions correlated with lattice constant and cohesive energy.

Modeled bulk modulus of ABO3 perovskites using transferred knowledge.

Demonstrated improved efficiency over traditional symbolic regression methods.

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.