Machine Learning Enabled Advanced Electron Tomography for Resolving Chemical Inhomogeneity and Materials Dynamics in Lithium-Ion Battery Electrodes
Xin, Huolin · 2025
Read Machine Learning Enabled Advanced Electron Tomography for Resolving Chemical Inhomogeneity and Materials Dynamics in Lithium-Ion Battery Electrodes by Xin, Huolin (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/doe-osti-3020361-machine-learning-enabled-advanced-electr.txt.
Description
Huolin Xin's final project report for DOE award DE-SC0021204, from the University of California, Irvine, covers a project that ran from September 2020 to August 2025. The goal was to watch battery electrodes at atomic scale while they work. Xin's team built machine learning tools for electron microscopy, together with three-dimensional, cryogenic, and in-situ imaging, to reveal chemical unevenness inside lithium-ion and lithium-metal battery materials.
The group released the TEMImageNet training library and AtomSegNet models that find, sharpen, and map atoms in noisy microscope images. They also built a transfer learning model that separates mixed manganese oxidation states in spectroscopy data. Applied to all-solid-state batteries, the imaging showed failure starting at cathode-electrolyte boundaries through surface frustration and interlayer shear. The methods suit beam-sensitive materials that ordinary microscopy damages.
Catalog record
| CREATOR | Xin, Huolin |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 11 KB |
| LICENSE | Public Domain |
| RIGHTS | PUBLIC DOMAIN |
| SOURCE | DOE OSTI |