English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Segmentation of 3D micro-Computed Tomographic uCT) images of rock samples isessential for further Digital Rock Physics (DRP) analysis, however,conventional methods such as thresholding, watershed segmentation, andconverging active contours are susceptible to user-bias. Deep ConvolutionalNeural Networks (CNNs) have produced accurate pixelwise semantic segmentationresults with natural images and $\mu$CT rock images, however, physical accuracyis not well documented. The performance of 4 CNN architectures is tested for 2Dand 3D cases in 10 configurations. Manually segmented uCT images of Mt. SimonSandstone are treated as ground truth and used as training and validation data,with a high voxelwise accuracy (over 99%) achieved. Downstream analysis is thenused to validate physical accuracy. The topology of each segmented phase iscalculated, and the absolute permeability and multiphase flow is modelled withdirect simulation in single and mixed wetting cases. These physical measures ofconnectivity, and flow characteristics show high variance and uncertainty, withmodels that achieve 95\%+ in voxelwise accuracy possessing permeabilities andconnectivities orders of magnitude off. A new network architecture is alsointroduced as a hybrid fusion of U-net and ResNet, combining short and longskip connections in a Network-in-Network configuration. The 3D implementationoutperforms all other tested models in voxelwise and physical accuracymeasures. The network architecture and the volume fraction in the dataset (andassociated weighting), are factors that not only influence the accuracytrade-off in the voxelwise case, but is especially important in training aphysically accurate model for segmentation.

Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images