Improving Performance Prediction of Electrolyte Formulations with Transformer-based Molecular Representation Model

TL;DR

This paper presents a transformer-based molecular representation model that improves the accuracy of predicting electrolyte formulation performance in batteries, demonstrating superior results over existing methods.

Contribution

Introduces a novel transformer-based model for electrolyte representation, enhancing machine learning predictions of battery electrolyte properties.

Findings

Outperforms state-of-the-art methods in battery property prediction tasks.

Effectively captures complex interactions in electrolyte formulations.

Provides a robust and efficient molecular representation for energy storage applications.

Abstract

Development of efficient and high-performing electrolytes is crucial for advancing energy storage technologies, particularly in batteries. Predicting the performance of battery electrolytes rely on complex interactions between the individual constituents. Consequently, a strategy that adeptly captures these relationships and forms a robust representation of the formulation is essential for integrating with machine learning models to predict properties accurately. In this paper, we introduce a novel approach leveraging a transformer-based molecular representation model to effectively and efficiently capture the representation of electrolyte formulations. The performance of the proposed approach is evaluated on two battery property prediction tasks and the results show superior performance compared to the state-of-the-art methods.