Murakami et al. Supplemental Data for "Microstructural Analysis of Li-Ion Conductors with Deep Learning and SEM Images"

For details, please refer to the paper: Murakami et al., "Deep Learning–Based SEM Image Analysis for Predicting Ionic Conductivity in LiZr₂(PO₄)₃-Based Solid Electrolytes". DOI: 10.1039/d5dd00232jdata_table.xlsx:Description of columns in the dataset (Excel file):sample.No: Sample index number.Ca, Si, Li, Zr, P: Elemental composition of each sample (Li1+2x+yCaxZr2-xSiyP3-yO12)1st heating temperature, 2nd heating temperature: The first and second sintering temperatures of the sample.Measured_Li_conductivity, Measured_Li_conductivity (Log): Experimentally measured lithium-ion conductivity (S cm⁻¹ at 30 °C) and its logarithmic value.pred_1 (Log), pred_2 (Log), pred_3 (Log), pred_mean (Log): Predicted lithium-ion conductivities obtained by regression analysis (logarithmic values). The first three columns correspond to predictions from individual SEM images, and the last column is their average.Reference: Source of the data.Reference 1: H. Takeda et al., Next Materials 8 (2025) 100574, https://doi.org/10.1016/j.nxmate.2025.100574Reference 2: H. Takeda et al., Mater. Adv., 3 (2022) 8141–8148, https://doi.org/10.1039/D2MA00731BNumber of SEM pictures: Number of SEM images obtained for each sample.SEM_images.zip:These files consists of SEM images and numerical datasets (descriptors and objective variables) of composition, sintering temperature, and ionic conductivities for 52 samples (1-3 SEM images are included per 1 sample, total 130 images)python_codes_rev1.zip:Python codes for four convolutional neural network (CNN) models used to investigate the relationship between these image data and ionic conductivity are provided. (revised n 15th Oct.)The program was verified to run successfully under the following environment:Python: 3.7.10 (see also requirements.txt)cuDNN: 7.6.5CUDA: 10.2GPU: NVIDIA GeForce RTX 2080 Tirequirements.txt:python environments for python_codes_rev1.zip.Segmentation_images.zip:Positive and negative segmentation images for Li ionic conductivities in LCZSP materials. (See Figure 5 in the main text.) List of sample#, compositions and process conditions (heating temperatures are also included as csv formatted file.