AI-Driven Characterization of Composite Electrode Microstructures in Solid-State Batteries

Solid-state batteries (SSBs) represent a promising frontier in next-generation energy storage systems. This research focuses on the microstructural effects in composite electrodes for SSBs, utilizing electrochemical simulations based on Focused Ion Beam-Scanning Electron Microscopy (FIB-SEM) imaging.<br/>Key to this research is the examination of how processing conditions, particle morphology, particle size distribution, and composition influence the microstructure of composite electrodes. These factors critically determine the residual porosity and homogeneity of the microstructure, which in turn directly impact the effectiveness of current pathways^1-4 and the active interface area^3,5,6 within the composite electrodes. Ultimately, these microstructural aspects affect battery performance, making their understanding and control essential for designing more efficient and durable SSBs.<br/>We will discuss U-Net neural networks for efficient image segmentation and processing of (FIB-)SEM images, focusing on cathode composites that feature sulfide solid electrolytes, such as Li₆PS₅Cl, and NCM cathode materials, such as Li_xNi_0.8Co_0.1Mn_0.1O₂. Synthetic datasets are used for training, and the segmentation model is validated against experimental data. This AI-driven approach is intended to facilitate a detailed and accurate characterization of microstructural features, where simulations of electrochemical behaviors and performance predictions can be based on.<br/>While the primary focus is on lithium-based SSBs, the findings are likely applicable to other systems, such as potassium- and sodium-based SSBs, due to the similar challenges and mechanisms involved in their microstructural optimization. Consequently, the insights gained from this research extend beyond lithium, offering valuable implications for the development of various next-generation energy storage systems.<br/>This study enhances the fundamental understanding of how microstructural characteristics influence the performance of SSBs. The interplay between microstructure and material design is critical, and this work exemplifies how advanced characterization and AI/ML applications can drive the discovery and optimization of next-generation energy storage materials and cell designs.<br/><br/>References<br/><br/>(1) Bielefeld, A.; Weber, D. A.; Janek, J. Modeling Effective Ionic Conductivity and Binder Influence in Composite Cathodes for All-Solid-State Batteries. <i>ACS Appl. Mater. Interfaces </i><b>2020</b>, <i>12</i> (11), 12821-12833.<br/>(2) Minnmann, P.; Quillman, L.; Burkhardt, S.; Richter, F. H.; Janek, J. Editors’ Choice--Quantifying the Impact of Charge Transport Bottlenecks in Composite Cathodes of All-Solid-State Batteries. <i>J. Electrochem. Soc. </i><b>2021</b>, <i>168</i> (4), 040537.<br/>(3) Minnmann, P.; Schubert, J.; Kremer, S.; Rekers, R.; Burkhardt, S.; Ruess, R.; Bielefeld, A.; Richter, F. H.; Janek, J. Editors' Choice—Visualizing the Impact of the Composite Cathode Microstructure and Porosity on Solid-State Battery Performance. <i>Journal of The Electrochemical Society </i><b>2024</b>. DOI: 10.1149/1945-7111/ad510e.<br/>(4) Schlautmann, E.; Weiß, A.; Maus, O.; Ketter, L.; Rana, M.; Puls, S.; Nickel, V.; Gabbey, C.; Hartnig, C.; Bielefeld, A.; et al. Impact of the Solid Electrolyte Particle Size Distribution in Sulfide-Based Solid-State Battery Composites. <i>Advanced Energy Materials </i><b>2023</b>. DOI: 10.1002/aenm.202302309.<br/>(5) Bielefeld, A.; Weber, D. A.; Janek, J. Microstructural Modeling of Composite Cathodes for All-Solid-State Batteries. <i>J. Phys. Chem. C </i><b>2019</b>, <i>123</i> (3), 1626-1634.<br/>(6) Bielefeld, A.; Weber, D. A.; Ruess, R.; Glavas, V.; Janek, J. Influence of Lithium Ion Kinetics, Particle Morphology and Voids on the Electrochemical Performance of Composite Cathodes for All-Solid-State Batteries. <i>J. Electrochem. Soc. </i><b>2022</b>, <i>169</i> (2), 020539.