Deep Learning-Based Automatic Segmentation Model for Micropores in Bituminous Coal HRTEM Images
Rapid and reproducible segmentation of pore-like gaps in coal high-resolution transmission electron microscopy (HRTEM) images is valuable for quantitative microstructural analysis. We developed WT-UNet from a VGG-encoder U-Net by replacing conventional decoder-side detail convolution in all four feature-fusion stages with wavelet convolution (WTConv). The data set comprised 53 manually annotated original HRTEM images from 14 bituminous coals and 3896 retained pore regions after physical-scale harmonization. A coal-sample-level split assigned 37 images from ten coals to training, 8 images from two coals to validation, and 8 images from two other coals to independent testing. Training-only geometric and brightness transformations produced 222 training pairs. On the independent test set, WT-UNet achieved 92.73% pixel accuracy, 45.15% mean intersection over union (mIoU), 60.34% mean pixel accuracy (mPA), and 28.63% mean pore-class IoU (mIoUpore). The corresponding U-Net values were 92.58%, 44.07%, 58.96%, and 27.19%, while FCN-ResNet50 and DeepLabV3-ResNet50 achieved mIoUs of 42.88% and 43.30%. WT-UNet obtained the best aggregate performance among the four models and improved the IoU of all three pore-size categories relative to the matched U-Net. These results demonstrate that decoder-side wavelet feature processing improves multiscale pore representation and provides an efficient automatic tool for HRTEM pore-image analysis.
Authors
- Meifen Li (ORCID: https://orcid.org/0000-0003-3241-4681)
- Yao Li (ORCID: https://orcid.org/0000-0001-5317-6446)
- Yungang Zhao
- Wang Qiu
- Xiaoyan Bai
Institutions
- China Coal Technology and Engineering Group Corp (China) (CN)
- China Coal Research Institute (China) (CN)
- Taiyuan University of Technology (CN)
Publication Details
- Journal
- ACS Omega
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1021/acsomega.6c08607
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00