Big Data of Materials Science: Critical Role of the Descriptor

TLDR

Statistical learning of materials properties begins with selecting descriptive parameters, yet when the connection between descriptors and underlying mechanisms is unclear, the causality of learned relationships is uncertain, undermining trustworthy predictions, anomaly detection, and scientific progress. The study analyzes the issue of descriptor selection and defines requirements for a suitable descriptor. The authors propose systematic criteria for selecting descriptors. Using the energy difference between zinc blende/wurtzite and rocksalt semiconductors as an example, the authors show how a meaningful descriptor can be systematically identified.

Abstract

Statistical learning of materials properties or functions so far starts with a largely silent, nonchallenged step: the choice of the set of descriptive parameters (termed descriptor). However, when the scientific connection between the descriptor and the actuating mechanisms is unclear, the causality of the learned descriptor-property relation is uncertain. Thus, a trustful prediction of new promising materials, identification of anomalies, and scientific advancement are doubtful. We analyze this issue and define requirements for a suitable descriptor. For a classic example, the energy difference of zinc blende or wurtzite and rocksalt semiconductors, we demonstrate how a meaningful descriptor can be found systematically.