Abstract

Descriptive geological data such as core, thin section and outcrop data, is pivotal for understanding our planet’s past, present, and future. Despite this richness, extracting meaningful insights from core description poses significant challenges due to the inherent complexity and variability of the data, the amount of existing material, and the subjectivity of the interpreter.

Focusing largely (but not exclusively) on carbonate rocks, characterized by their heterogeneity at all observational scales, I will discuss how my research group and I have pioneered the application of deep-learning computer vision to geological core interpretation. This technology transcends the traditional, tedious manual interpretations of cores, offering a rapid, and often more accurate, alternative for delineating depositional environments and sequence stratigraphy. Convolutional neural networks (CNNs) form the backbone of our approach, enabling us to process core data with unprecedented efficiency. I will show that these sophisticated models, when correctly trained and fed with substantial datasets, serve as invaluable tools for geologists, outpacing conventional methods in speed without compromising on precision.

Our early work was centred on transfer learning, an AI approach that adapts pre-existing models to new data. I will show that this remains one of the best way to train classification algorithms for geological dataset. But we also worked on generative algorithms that fill gaps in our sampling of core imagery: for instance, we use Generative Adversarial Networks (GANs) to transform the resistivity images from formation micro scanners into representations mirroring actual core photographs, thus enhancing the interpretability for geologists irrespective of their background in downhole tools.

We tackle the often-limiting factor of dataset size in two ways. First, we recourse to generative AI to oversample our training set. Second, we also explore semi-supervised learning techniques.  I will demonstrate that we successfully train models on core deformation images from IODP with minimal labelled data, achieving accuracy on par with, if not exceeding, that of transfer learning models.

Results from my research group and the broader research community indicate a promising future where deep learning not only streamlines the interpretation process but also provides robust, systematic insights that could revolutionize our understanding of Earth history and of subsurface georesources.

Biography

Professor John is head of Data Science and the Environment at the Digital Environments Research Institute (DERI) at Queen Mary University of London. After completing his undergraduate degree in Geology from the University of Neuchâtel in Switzerland, he pursued a PhD in carbonate sedimentology at the University of Potsdam (Germany), and a postdoc at the University of California, Santa Cruz.

Prof John then served as a staff scientist with the U.S. Implementing organization of the International Ocean Drilling Program in College Station, Texas, where his role included planning and leading scientific drilling expeditions at sea. He obtained his first faculty position in 2006, as a lecturer (assistant professor) in the Department of Earth Science and Engineering, being subsequently promoted up to Reader (Full Professor) in Earth-Centric AI in 2018. He assumed his professorship at DERI in January 2024.

Cédric’s research is characterized by its breadth, encompassing carbonate systems, field geology, geochemistry, alongside computational methods, and data science. At the moment, he is particularly interested in the disruptive power that deep learning methods have in geosciences, and how this could revolutionize the way Earth Scientists work. For more information on Professor John's research and his team's work, visit www.john-lab.org.