Naturally-meaningful and efficient descriptors: machine learning of material properties based on robust one-shot ab initio descriptors
This work addresses the need for efficient and meaningful descriptors in materials science, offering a domain-specific improvement for ML-based property prediction.
The authors tackled the problem of discovering novel materials by proposing ROSA descriptors, which are computationally cheap and accurately predict a range of material properties, achieving accurate predictions across various crystal structures and molecules.
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.