Joshua Griffiths

We have developed a generalisable machine learning framework for reservoir quality prediction in deeply buried clastic systems. Applied to the Lower Jurassic deltaic sandstones of the Tilje Formation (Halten Terrace, North Sea), the approach integrates sedimentological facies modelling with mineralogical and petrophysical prediction in a single workflow. Using supervised Extreme Gradient Boosting (XGBoost) models, we classify reservoir facies, predict permeability directly from standard wireline log parameters and estimate the abundance of porosity-preserving grain coating chlorite (gamma ray, neutron porosity, caliper, photoelectric effect, bulk density, compressional and shear sonic, and deep resistivity). Model development and evaluation employed stratified K-fold cross-validation to preserve facies proportions and mineralogical variability across folds, supporting robust performance assessment and testing generalisability across a geologically heterogeneous dataset. Core description, point count petrography, and core plug analyses were used for ground truthing. The models distinguish chlorite-associated facies with up to 80% accuracy and estimate permeability with a mean absolute error of 0.782 log(mD), improving substantially on conventional regression-based approaches. The models also enable prediction, for the first time using wireline logs, grain-coating chlorite abundance with a mean absolute error of 1.79% (range 0–16%). The framework takes advantage of diagnostic petrophysical responses associated with chlorite and high porosity, yielding geologically consistent and interpretable results. It addresses persistent challenges in characterising thinly bedded, heterogeneous intervals beyond the resolution of traditional methods and is transferable to other clastic reservoirs, including those considered for carbon storage and geothermal applications. The workflow supports cost-effective, high-confidence subsurface characterisation and contributes a flexible methodology for future work at the interface of geoscience and machine learning.

In the quest to use modern analogues to understand clay mineral distribution patterns to better predict clay mineral occurrence in ancient and deeply buried sandstones, it has been necessary to define palaeo sub-environments from cores through modern sediment successions. Holocene cores from Ravenglass in the NW of England, United Kingdom, contained metre-thick successions of massive sand that could not be unequivocally interpreted in terms of palaeo sub-environments using conventional descriptive logging facies analysis. We have therefore explored the use of geochemical data from portable X-ray fluorescence analyses, from whole-sediment samples, to develop a tool to uniquely define the palaeo sub-environment based on geochemical data. This work was carried out through mapping and defining sub-depositional environments in the Ravenglass Estuary and collecting 497 surface samples for analysis. Using R statistical software, we produced a classification tree based on surface geochemical data from Ravenglass that can take compositional data for any sediment sample from the core or the surface and define the sub-depositional environment. The classification tree allowed us to geochemically define ten out of eleven of the sub-depositional environments from the Ravenglass Estuary surface sediments. We applied the classification tree to a core drilled through the Holocene succession at Ravenglass, which allowed us to identify the dominant paleo sub-depositional environments. A texturally featureless (massive) metre-thick succession, that had defied interpretation based on core description, was successfully related to a palaeo sub-depositional environment using the geochemical classification approach. Calibrated geochemical classification models may prove to be widely applicable to the interpretation of sub-depositional environments from other marginal marine environments and even from ancient and deeply buried estuarine sandstones.