Search papers, labs, and topics across Lattice.
This study utilizes a frozen self-supervised vision-transformer encoder paired with a lightweight trainable decoder to enhance the data efficiency of crack quantification in lithium-ion cathodes, addressing the challenge of labor-intensive pixel-level annotation in quantitative microscopy. By applying this method to high-resolution electron microscopy images of NMC cathodes, the researchers successfully differentiate between various types of cracks and quantify their characteristics across different aging states. The findings reveal significant increases in late intergranular crack coverage in cycled samples, suggesting that degradation is primarily driven by electrochemical cycling rather than temperature effects, which is crucial for improving battery design and longevity.
A single destructive image can now yield comprehensive population-level statistics on crack degradation in lithium-ion cathodes, transforming how we assess battery aging.
Battery lifetime is central to sustainable electrification, yet the particle cracking that drives lithium-ion cathode aging is hard to measure: quantitative microscopy of this degradation is bottlenecked by annotation, because each destructive electron-microscopy cross-section spans hundreds of megapixels and pixel-level expert labelling requires hours per image. We show that a frozen self-supervised vision-transformer encoder, combined with a lightweight trainable decoder and iterative model-assisted annotation, turns this sparse labelling budget into population-scale degradation measurements. Applied to three 120-megapixel NMC cathode cross-sections representing initial, cycled-aged and calendar-aged states, the framework distinguishes intragranular cracks from early- and late-stage intergranular cracks and yields per-particle distributions of crack width, tortuosity and area fraction. Late intergranular crack coverage reaches 4.6% in the cycled sample versus 0.5% in the initial and calendar-aged samples, forming more tortuous, higher-coverage networks, consistent with degradation from repeated electrochemical cycling rather than elevated-temperature storage alone. A single destructive image yields the population-level statistics needed for lifetime-extending design, aging assessment and second-life decisions.
