Unlocking anode-free battery performance: AI-enhanced electron microscopy for deciphering layered cathode interfaces

Document Type

Article

Publication Date

5-1-2026

Abstract

The pursuit of high-energy-density anode-free batteries (AFBs) has shifted the research focus toward the fundamental understanding of structural stability and interfacial chemistry. Layered cathode materials are central to this transition, yet their practical application in AFBs is hindered by complex failure mechanisms such as lattice strain and parasitic side reactions. This review systematically traces the evolution of advanced transmission electron microscopy (TEM) and its pivotal role in elucidating the structure-property relationships of these electrode materials. By integrating artificial intelligence (AI) and machine learning (ML) for high-throughput data processing, we highlight how modern characterization overcomes traditional limitations in image denoising and automated defect recognition. The discussion encompasses both lithium and sodium-ion systems, focusing on in situ and cryogenic TEM techniques that reveal real-time ion migration, phase transformations, and the evolution of fragile solid-electrolyte interphases. Furthermore, we emphasize the interdisciplinary synergy between electron microscopy and AI as a necessity for the “mechanism-driven” design of next-generation and high-stability batteries. This review provides critical insights into addressing the bottlenecks of layered cathode configurations. Furthermore, this review discusses the emerging role of AI in integrating fragmented research data into structured knowledge graphs. By organizing highly heterogeneous experimental findings into relational networks, AI can uncover latent structure-performance correlations, offering a data-driven roadmap for mechanism-guided material design and advanced characterization.

Keywords

Anode-free batteries, Artificial intelligence, In situ electron microscopy, Layered cathode interfaces, Structural stability

Publication Title

Energy Storage Materials

ISSN

2405-8297

DOI

10.1016/j.ensm.2026.105111

Funders

Hefei University of Technology

Volume

88

Publisher

Elsevier B.V.

Share

COinS