GO-Forward hosts regular webinars inviting exciting guest speakers on topics such as geothermal exploration, forward modeling.
We attend and present at various international conferences. We will keep you updated on times and places we will present research output from GO-Forward.
Carbonate platforms record the interplay of biological production, relative sea-level change, and sediment transport, yet disentangling these controls from the stratigraphic record alone remains notoriously difficult. Stratigraphic forward modelling offers a way to test conceptual models quantitatively, but existing tools are often closed-source, hard to extend, or built around clastic-systems assumptions that do not transfer cleanly to carbonates.
In this talk we will introduce CarboKitten.jl, an open-source Julia package for simulating marine carbonate platform stratigraphy. At its core is the ALCAP model, which couples a mechanism of biological interactions among carbonate-producing organisms with light-limited production curves and an active-layer transport scheme that distinguishes in-situ from transported sediment. Depth-dependent diffusivities follow empirically grounded formulations. A modular component architecture makes it straightforward to swap processes such as production, transport, denudation, subsidence, sea-level forcing to isolate their contributions. In designing CarboKitten.jl, we prioritized the speed of runs and attractive, publication-quality graphics, but the architecture is open for further features.
We will demonstrate the package through a few example simulations, highlighting the kinds of geological hypotheses it lets us test and outline how built-in diagnostics (Wheeler diagrams, stratigraphic columns, sediment profiles). I will close with current developments and an invitation to the community to use, extend, and contribute to the tool.
Dr. Michael Welch (DTU – Technical University of Denmark) and Lucy Salmon (Swiss Geo Energy SA) present a physics-based forward modelling tool for fracture network growth. Using data about the geological evolution of a reservoir, it models komplex fracture networks based on physics rather than statistics. Multiple realizations of such networks can be created, which are all geologically consistent, to perform uncertainty – and sensitivity analysis.
Learn more on LinkedIn.
Carbonate rocks exhibit heterogeneities from the seismic scale to the pore level, which pose challenges in interpretation, especially in mixed carbonate-clastic systems. Aside from the well-known ‘scale gap’ issue where heterogeneities change depending on the scale of observation, humans also lack consistency in how they interpretate observational data. Accurate interpretation of carbonate grains and textures is essential for deducing depositional environments and stratigraphic sequences. Traditional manual interpretation of geological data is labour-intensive and often prone to inaccuracies, potentially leading to flawed subsurface models. In this talk, I will present over eight years of research from my team on using computer vision to enhance the interpretation of geological data in these complex systems, focusing on core images, logs, and seismic data, mostly coming from ODP Leg 194 (a Miocene mixed carbonate-clastic system).
Our research has shown that convolutional neural networks (CNNs) can inter-pret core data with greater speed and accuracy than experienced geologists. This approach is cost-effective and biases from the models can be mitigated through visual inspection of edge cases and the consistency of bias across different wells and basins. Transfer learning has been pivotal, along with trials in individual grain classification.
Furthermore, we have utilized generative AI to assist geologists in interpreting formation microscanner (FMS) images, converting them into core image repre-sentations that are more intuitive, especially beneficial for carbonate texture in-terpretation. While the technique performs better with finer textures, it supports geologists at varying expertise levels.
Lastly, our computer vision work with seismic data has two significant applica-tions. One is the upscaling of historical single-channel seismic data to approxi-mate the quality of modern multi-channel data, potentially reviving interest in basins once overlooked for geo-energy storage. The second application involves the use of deep-learning methods for the automatic interpretation of sequence stratigraphy from seismic data, which we’ll explore alongside the role of syn-thetic data in this field.
Professor Cédric M. John holds the position of head of Data Science and the Environment at the Digital Environments Research Institute (DERI) at Queen Mary University of London. He began his academic path with a diploma in Geology from the University of Neuchâtel in Switzerland in 1999, followed by a doctorate from Potsdam University in Germany in 2003.
Post-PhD, Cédric undertook a postdoctoral fellowship at UC Santa Cruz from 2004 to 2005, then served as a staff scientist with the USIO in College Station, Texas, until 2006. He transitioned to academia in June 2006 as a lecturer at the Department of Earth Science and Engineering, later advancing to Senior Lecturer in 2011, and to Reader 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. He is particularily interested in the (sequence) stratigraphy of carbonate systems, and computational methods that allow geologists to emulate stratigraphic processes over geological timescales. For more information on Professor John’s research and his team’s work, please visit www.john-lab.org.