Unconventional/complex reservoirs

Machine-Learning Techniques Characterize Source-Rock Images at the Pore Scale

The paper demonstrates the ability of deep-learning generative models to enable new shale-characterization methods.

Image-based characterization and deep-learning work flow
Fig. 1—Image-based characterization and deep-learning work flow. Images are first acquired for a source-rock sample from one or multiple modalities. The image data then are curated, including alignment, normalization, and subsampling, to create a data set suitable for machine-learning model training. After training the image-processing model, new images are generated or predicted. The synthesized images are post-processed, including segmentation into pore and mineral phases, and the morphological and petrophysical properties of the sample evaluated.

Nanoimaging techniques for characterizing pore-scale structure of shales trade off between high-resolution/high-contrast sample-destructive imaging modalities and low-contrast/low-resolution sample-preserving modalities. Acquisition of nanoscale images also is often time-consuming and expensive. In the complete paper, the author introduces methods for overcoming these challenges in image-based characterization of the fabric of shale source rocks using deep-learning models.


A promising application of data-driven scale-translation techniques is nanoscale imaging. This application is important for studying shales because of the importance of nanoporosity in shale gas storage.

Restricted Content
We're sorry, but this content is reserved for SPE Members. If you are a member, please sign in at the top of the page for access. If you are not a member and you find JPT content valuable, we encourage you to become a part of the SPE member community.