Extracting a Database of Challenges and Mitigation Strategies for Sodium-ion Battery Development

Mrigi Munjal, Thorben Prein, Vineeth Venugopal, Kevin J Huang, Elsa Olivetti

Submission Track: Papers

Submission Category: AI-Guided Design

Keywords: Natural Language Processing, Sodium-ion Batteries

TL;DR: We utilized Natural Language Processing techniques to extract and assess challenges and corresponding mitigation strategies to inform the scale-up of sodium-ion batteries.

Abstract: Sodium-ion batteries (SIBs) are emerging as a promising solution for grid-scale energy storage applications due to the widespread availability of sodium and the anticipated cost-effectiveness. The manufacturing expertise established for lithium-ion batteries (LIBs) offers a solid foundation for the development of SIBs. However, to realize their full potential, specific challenges related to the synthesis and performance of electrode materials in SIBs must be overcome. This work extracts a large database of challenges limiting the performance and synthesis of SIB cathode active materials (CAMs) and pairs these challenges with corresponding proposed mitigation strategies from the SIB literature by employing custom natural language processing (NLP) tools. The database is meant to help scientists expedite the development and exploration of SIBs.

Submission Number: 31