Element similarity in high-dimensional materials representations

TL;DR

This paper evaluates high-dimensional element representations derived from various physical and computational sources, demonstrating their effectiveness in clustering elements and improving crystal structure prediction over traditional methods.

Contribution

It introduces and assesses high-dimensional element embeddings from multiple data sources, showing their utility in materials science applications.

Findings

Element embeddings cluster into familiar groups.

Cosine similarity outperforms traditional radius ratio rules.

Embeddings improve crystal structure classification.

Abstract

The traditional display of elements in the periodic table is convenient for the study of chemistry and physics. However, the atomic number alone is insufficient for training statistical machine learning models to describe and extract composition-structure-property relationships. Here, we assess the similarity and correlations contained within high-dimensional local and distributed representations of the chemical elements, as implemented in an open-source Python package ElementEmbeddings. These include element vectors of up to 200 dimensions derived from known physical properties, crystal structure analysis, natural language processing, and deep learning models. A range of distance measures are compared and a clustering of elements into familiar groups is found using dimensionality reduction techniques. The cosine similarity is used to assess the utility of these metrics for crystal structure prediction, showing that they can outperform the traditional radius ratio rules for the structural classification of AB binary solids.