Semantic Embeddings of Chemical Elements for Enhanced Materials Inference and Discovery

TL;DR

This paper introduces ElementBERT, a domain-specific language model trained on alloy literature to generate semantic embeddings of elements, significantly improving materials property prediction and discovery tasks.

Contribution

The authors develop ElementBERT, a specialized BERT model for alloys, providing superior elemental descriptors that enhance materials inference over traditional methods.

Findings

ElementBERT outperforms general BERT models in alloy-related tasks.

Semantic embeddings improve prediction accuracy by up to 23%.

The framework accelerates materials discovery and optimization.

Abstract

We present a framework for generating universal semantic embeddings of chemical elements to advance materials inference and discovery. This framework leverages ElementBERT, a domain-specific BERT-based natural language processing model trained on 1.29 million abstracts of alloy-related scientific papers, to capture latent knowledge and contextual relationships specific to alloys. These semantic embeddings serve as robust elemental descriptors, consistently outperforming traditional empirical descriptors with significant improvements across multiple downstream tasks. These include predicting mechanical and transformation properties, classifying phase structures, and optimizing materials properties via Bayesian optimization. Applications to titanium alloys, high-entropy alloys, and shape memory alloys demonstrate up to 23% gains in prediction accuracy. Our results show that ElementBERT surpasses general-purpose BERT variants by encoding specialized alloy knowledge. By bridging contextual insights from scientific literature with quantitative inference, our framework accelerates the discovery and optimization of advanced materials, with potential applications extending beyond alloys to other material classes.