A dataset and benchmark of carbonate thin-section images for deep learning | Scientific Data

Nature·Jan 28

✦ NabkaNews BriefAuto-summarized from multiple outlets · verify with the source

A dataset of carbonate thin-section images has been released for use in deep learning applications. The dataset appears to be part of a broader effort to develop and apply machine learning techniques to the analysis of rock microstructures, with various studies exploring its use in classifying minerals and interpreting rock microstructures. The dataset may include images from specific geological formations, such as those in China and Brazil.

Full coverage

High-resolution Annotated Dataset of Girvanella Boundstone Microfacies from the Xiannüdong Formation, China

Nature·Mar 5

A Photomicrographic Dataset of Rocks for the Accurate Classification of Minerals

Nature·Nov 11

Petrographic image classification of complex carbonate rocks from the Brazilian pre-salt using convolutional neural networks

Nature·Aug 21

A benchmark dataset and baseline methods for rock microstructure interpretation in SEM images

Nature·Oct 22

On the generation of realistic synthetic petrographic datasets using a style-based GAN

Nature·Jul 27

View original report at Nature ↗