Modeling High Entropy Alloys' Mechanical Property through Natural Language-Derived Descriptors

TL;DR

This paper demonstrates that natural language-derived descriptors of alloy processing treatments can effectively predict high-entropy alloys' hardness, significantly improving machine learning models' accuracy.

Contribution

It introduces a novel approach using transformer embeddings of processing descriptions as descriptors to enhance alloy property prediction.

Findings

Transformer embeddings can reconstruct processing parameters with R2>0.99.

Using language-derived descriptors improves alloy hardness prediction by 20%.

Natural language processing enhances alloy design models.

Abstract

Processing treatments of alloys, despite being influential to alloy properties, are often neglected in machine-learning aided alloy designs due to the difficulties in expressing this information. We investigated the expressiveness of transformer embeddings through synthesized annealing processing treatment text and verified that embeddings could be utilized to reconstruct the processing parameters of alloys effectively with an R2>0.99. We then utilized the vector representations of alloys' processing treatment descriptions as descriptors to model high-entropy alloys' hardness and achieved a 20% improvement in prediction, verifying that natural language-derived descriptors of processing treatment information could be utilized to improve prediction of alloy properties.