Descriptors for Machine Learning of Materials Data

2017/09/06 by Atsuto Seko, Atsushi Togo, Seko, Atsuto +3
Materials Science · Physics and Astronomy · #FOS: Physical sciences #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci) #X-ray Diffraction in Crystallography #cond-mat.mtrl-sci

paper · pdf · doi:10.48550/arxiv.1709.01666

12 pages, 10 figures

arxiv created 2017/09/06 · openalex publication_date 2017/09/06 · arxiv updated 2017/09/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Representations of Materials for Machine Learning
• Structure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties
• Atomistic graph networks for experimental materials property prediction
• What Information is Necessary and Sufficient to Predict Materials Properties using Machine Learning?
• Learning to Make Chemical Predictions: the Interplay of Feature Representation, Data, and Machine Learning Algorithms