Data-driven development of cycle prediction models for lithium metal batteries using multi modal mining

TL;DR

This paper presents a novel multi modal data-driven approach using an integrated platform with LLM and graph mining to accurately predict capacity and stability of lithium metal batteries, validated through experiments.

Contribution

Introduction of a new multi modal data collection platform combining LLM and graph mining for battery data extraction and the first machine learning models for predicting lithium metal battery performance.

Findings

Accurate extraction of battery data from diverse sources.

First machine learning models for lithium metal battery prediction.

Experimental validation confirms practical applicability.

Abstract

Recent advances in data-driven research have shown great potential in understanding the intricate relationships between materials and their performances. Herein, we introduce a novel multi modal data-driven approach employing an Automatic Battery data Collector (ABC) that integrates a large language model (LLM) with an automatic graph mining tool, Material Graph Digitizer (MatGD). This platform enables state-of-the-art accurate extraction of battery material data and cyclability performance metrics from diverse textual and graphical data sources. From the database derived through the ABC platform, we developed machine learning models that can accurately predict the capacity and stability of lithium metal batteries, which is the first-ever model developed to achieve such predictions. Our models were also experimentally validated, confirming practical applicability and reliability of our data-driven approach.