Data from: Geo-SegNet: A contrastive learning enhanced U-Net for geomaterial segmentation

Public

  • The dataset was obtained using high-resolution X-ray micro-CT scans with a TESCAN UniTOM XL scanner at Duke University’s Creativ Engineering Laboratory. Samples were secured with a custom core holder featuring a magnetic aluminum base and stabilized using an acrylic tube. Scanning parameters included 160 kV voltage, 20 W power, 4096 projections, 20 µm voxel size, and a 1.5 mm copper filter. The UniTOM XL’s helical scanning captured full core widths, and 9266 representative slices were selected to optimize computation and train models on pore feature segmentation.

Total Size
13 files (62.3 GB)
Data Citation
  • Tian, Q., Goodhue, S., Xiong, H., & Dalton, L. E. (2024). Data from: Geo-SegNet: A contrastive learning enhanced U-Net for geomaterial segmentation. Duke Research Data Repository. https://doi.org/10.7924/r4rf5zz3v
DOI
  • 10.7924/r4rf5zz3v
Publication Date
ARK
  • ark:/87924/r4rf5zz3v
Type
Title
  • Data from: Geo-SegNet: A contrastive learning enhanced U-Net for geomaterial segmentation
This Dataset
Usage Stats