| Title | Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin |
| |
| Author | Chen, Z ; Liu, X;
Yang, J; Little, E; Zhou, Y |
| Source | Computers and Geosciences vol. 138, 104450, 2020 p. 1-10, https://doi.org/10.1016/j.cageo.2020.104450 |
| Image |  |
| Year | 2020 |
| Alt Series | Natural Resources Canada, Contribution Series 20190066 |
| Publisher | Elsevier |
| Document | serial |
| Lang. | English |
| Media | paper; on-line; digital |
| File format | pdf; html |
| Province | Alberta |
| NTS | 72M; 73D; 73E; 73L; 73M; 74D; 82M; 82N; 82O; 82P; 83; 84A; 84B; 84C; 84D; 93A; 93H; 93I; 93P; 94A |
| Lat/Long WENS | -120.0833 -110.0500 57.0000 51.0000 |
| Subjects | mineralogy; sedimentology; fossil fuels; Science and Technology; Nature and Environment; scanning electron microscopy; bedrock geology; lithology; sedimentary rocks; shales; mineralogical analyses;
clays; modelling; textural analyses; petroleum resources; hydrocarbons; source rocks; Duvernay Shale; Western Canada Sedimentary Basin; Duvernay Formation; Methodology; Phanerozoic; Paleozoic; Devonian |
| Illustrations | photomicrographs; flow diagrams; histograms; schematic representations; plots |
| Program | Geoscience for New Energy Supply (GNES) Shale-hosted petroleum resource assessment |
| Released | 2020 02 15 |
| Abstract | Texture-based feature extraction and object segmentation are challenging in image processing. In this study, the U-Net architecture developed for biomedical image analysis was used to evaluate geologic
characteristics depicted within scanning electron microscope (SEM) images of shale samples. With a revised weight function, the U-Net architecture allowed for effective discrimination of clay aggregates mixed with matrix mineral particles and organic
matter (OM). In training, a local variability weight based on spatial statistics was used to enhance the contrast between features across boundary in the loss function of U-Net system optimization, thereby improving the ability of U-Net to
distinguish the geologic features specific to our research needs. The Tensorflow neural network library was used to create semantic segmentation and feature extraction models in mineral identification. In the application example of the Devonian
Duvernay shale study, we prepared 8000 randomly sliced image cuts (256 × 256 pixels) from four masked image tiles (6144 × 6144 pixels) with tagged feature objects, among which 6400 are for training and the remaining 1600 held image slices for
validation. In the validation, the average of intersection over union (IOU) reaches 91.7%. The trained model approved by validation was used for clay aggregate segmentation and mineral classification. Three hundred SEM image tiles of source rock
samples from different maturities in the Duvernay Formation were processed using the proposed workflow. The results show that the clay aggregates are clearly separated from other matrix mineral particles with acceptable boundaries, although both
exhibit indistinguishable grey-level pixels. This approach demonstrates that texture-based deep learning feature extraction is feasible, cost-effective and timely, and can help geoscientists gain new insights by quantitatively analyzing specific
geological characteristics and features. |
| Summary | (Plain Language Summary, not published)
Image classification based on text feature is difficult. In this study, we use machine learning technique to tackle the problem. A special deep
artificial neural network (U-net) developed for biomedical image analysis was used to evaluate geologic characteristics depicted within scanning electron microscope (SEM) images of shale samples, specifically for discriminating clay aggregates mixed
with matrix mineral particles and organic matter. Three hundred SEM images of source rock samples from different hydrocarbon zones in the Duvernay Formation were processed using the proposed method. The results show that the clay aggregates are
clearly separated from other matrix mineral particles with acceptable boundaries, although both exhibit indistinguishable gray-level pixels. This approach demonstrates that texture-based deep learning feature extraction is feasible, cost-effective
and timely, and can help geoscientists gain new insights by quantitatively analyzing specific geologic characteristics and features. |
| GEOSCAN ID | 314683 |
|
|