Efficient Structure-Informed Featurization and Property Prediction of Ordered, Dilute, and Random Atomic Structures

TL;DR

This paper introduces optimized featurization methods for atomic structures that significantly improve computational efficiency and prediction accuracy in materials informatics, applicable to ordered, dilute, and random structures.

Contribution

The authors propose structure-informed featurization techniques that reduce redundant calculations by leveraging crystallographic and representation-dependent equivalencies, enhancing efficiency and performance.

Findings

Performance increased by 2 to 10 times using new featurization methods.

Efficient algorithms for ordered, dilute, and random structures.

Implementation within pySIPFENN toolset.

Abstract

Structure-informed materials informatics is a rapidly evolving discipline of materials science relying on the featurization of atomic structures or configurations to construct vector, voxel, graph, graphlet, and other representations useful for machine learning prediction of properties, fingerprinting, and generative design. This work discusses how current featurizers typically perform redundant calculations and how their efficiency could be improved by considering (1) fundamentals of crystallographic (orbits) equivalency to optimize ordered cases and (2) representation-dependent equivalency to optimize cases of dilute, doped, and defect structures with broken symmetry. It also discusses and contrasts ways of (3) approximating random solid solutions occupying arbitrary lattices under such representations. Efficiency improvements discussed in this work were implemented within pySIPFENN or python toolset for Structure-Informed Property and Feature Engineering with Neural Networks developed by authors since 2019 and shown to increase performance from 2 to 10 times for typical inputs. Throughout this work, the authors explicitly discuss how these advances can be applied to different kinds of similar tools in the community.