Litcius/Paper detail

Generating multi-scale Li-ion battery cathode particles with radial grain architectures using stereological generative adversarial networks

Lukas Fuchs, Orkun Furat, Donal P. Finegan, Jeffery M. Allen, Francois L. E. Usseglio‐Viretta, Bertan Özdoğru, Peter J. Weddle, Kandler Smith, Volker Schmidt

2025Communications Materials11 citationsDOIOpen Access PDF

Abstract

Abstract Understanding structure-property relationships of Li-ion battery cathodes is crucial for optimizing rate-performance and cycle-life resilience. However, correlating the morphology of cathode particles, such as in LiNi0.8Mn0.1Co0.1O2 (NMC811), and their inner grain architecture with electrode performance is challenging, particularly, due to the significant length-scale difference between grain and particle sizes. Experimentally, it is not feasible to image such a high number of particles with full granular detail. A second challenge is that sufficiently high-resolution 3D imaging techniques remain expensive and are sparsely available at research institutions. Here, we present a stereological generative adversarial network-based model fitting approach to tackle this, that generates representative 3D information from 2D data, enabling characterization of materials in 3D using cost-effective 2D data. Once calibrated, this multi-scale model can rapidly generate virtual cathode particles that are statistically similar to experimental data, and thus is suitable for virtual characterization and materials testing through numerical simulations. A large dataset of simulated particles with inner grain architecture has been made publicly available.

Topics & Concepts

Characterization (materials science)Battery (electricity)CathodeComputer scienceScale (ratio)Materials scienceResilience (materials science)ScalingParticle (ecology)Data-drivenSimulationNanotechnologyArtificial intelligenceComposite materialPhysicsEngineeringElectrical engineeringMathematicsGeologyGeometryQuantum mechanicsOceanographyPower (physics)Medical Image Segmentation TechniquesGenerative Adversarial Networks and Image SynthesisCell Image Analysis Techniques
Generating multi-scale Li-ion battery cathode particles with radial grain architectures using stereological generative adversarial networks | Litcius