CEA-Liten Unveils New AI Method for Faster Analysis of Solid Oxide Cells (SOC) Materials
Read the full article here: https://doi.org/10.1016/j.matdes.2025.115200
CEA-Liten researchers have developed an innovative AI method that makes it faster and easier to analyse Solid Oxide Cell (SOC) materials. The team created a deep-learning workflow that automatically identifies different phases in scanning electron microscopy (SEM) images using a U-Net model trained with EDS-guided labels.
What sets this approach apart is that it delivers highly accurate results directly from SEM images, no additional data, such as energy-dispersive X-ray spectroscopy (EDS) mapping, is needed. This innovation could greatly speed up the study of SOC microstructures while reducing both effort and cost.
The research was carried out within the MatCHMaker project, funded by the European Union’s Horizon Europe programme. The team highlights the valuable collaboration and support of Thomas David, Laure Guetaz, Geoffrey Daniel, and Zineb Saghi.