Data-Driven Battery Characterization and Prognosis: Recent Progress, Challenges, and Prospects

Shanling Ji, Jianxiong Zhu, Yaxin Yang, Goncalo Dos Reis, Zhisheng Zhang

Research output: Contribution to journalReview articlepeer-review

Abstract / Description of output

Battery characterization and prognosis are essential for analyzing underlyingelectrochemical mechanisms and ensuring safe operation, especially with theassistance of superior data-driven artificial intelligence systems. This reviewprovides a unique perspective on recent progress in data-driven batterycharacterization and prognosis methods. First, recent informative imagecharacterization and impedance spectrum as well as high-throughputscreening approaches on revealing battery electrochemical mechanisms atmultiple scales are summarized. Thereafter, battery prognosis tasks andstrategies are described, with the comparison of various physics-informedmodeling strategies. Considering unlocking mechanisms from tremendousbattery data, the dominant role of physics-informed interpretable learning inaccelerating energy device development is presented. Finally, challenges andprospects on data-driven characterization and prognosis are discussed towardaccelerating energy device development with much-enhanced electrochemicaltransparency and generalization. This review is hoped to supply new ideasand inspirations to the next-generation battery development.
Original languageEnglish
Article number2301021
Number of pages17
JournalSmall Methods
Early online date11 Jan 2024
Publication statusE-pub ahead of print - 11 Jan 2024


Dive into the research topics of 'Data-Driven Battery Characterization and Prognosis: Recent Progress, Challenges, and Prospects'. Together they form a unique fingerprint.

Cite this