Descriptors for Machine Learning of Materials Data

TL;DR

This paper discusses how to effectively convert material compounds into descriptors suitable for machine learning models, facilitating improved analysis of materials data.

Contribution

It introduces methods to represent compounds as descriptors for machine learning, enabling better application to materials datasets.

Findings

Proposes a framework for representing compounds as descriptors

Demonstrates application of descriptors in machine learning models

Enhances the analysis of materials data using new representations

Abstract

Descriptors, which are representations of compounds, play an essential role in machine learning of materials data. Although many representations of elements and structures of compounds are known, these representations are difficult to use as descriptors in their unchanged forms. This chapter shows how compounds in a dataset can be represented as descriptors and applied to machine-learning models for materials datasets.