Naturally-meaningful and efficient descriptors: machine learning of material properties based on robust one-shot ab initio descriptors

TL;DR

This paper introduces ROSA descriptors, a computationally inexpensive and robust set of features derived from low-level ab initio calculations, enabling accurate machine learning predictions of various material properties across diverse structures.

Contribution

The paper presents ROSA descriptors, a novel class of material features that are easy to compute and highly effective for ML-based property prediction.

Findings

ROSA descriptors accurately predict multiple material properties.

ROSA descriptors are computationally cheap and easy to generate.

Effective across crystals, amorphized structures, MOFs, and molecules.

Abstract

Establishing a data-driven pipeline for the discovery of novel materials requires the engineering of material features that can be feasibly calculated and can be applied to predict a material's target properties. Here we propose a new class of descriptors for describing crystal structures, which we term Robust One-Shot Ab initio (ROSA) descriptors. ROSA is computationally cheap and is shown to accurately predict a range of material properties. These simple and intuitive class of descriptors are generated from the energetics of a material at a low level of theory using an incomplete ab initio calculation. We demonstrate how the incorporation of ROSA descriptors in ML-based property prediction leads to accurate predictions over a wide range of crystals, amorphized crystals, metal-organic frameworks and molecules. We believe that the low computational cost and ease of use of these descriptors will significantly improve ML-based predictions.