Dolomitization in the Western Canadian Sedimentary Basin has been extensively researched, producing vast geochemical datasets. This provides a unique opportunity to assess the regional sources and flux of dolomitizing fluids on a larger scale than previous studies. A meta‐analysis was conducted on stable isotope, strontium isotope (⁸⁷Sr/⁸⁶Sr), fluid inclusion and lithium‐rich formation water data published over 30 years, with new petrographic, X‐ray diffraction, stable isotope and rare‐earth element (REE+Y) data. The Middle to Upper Devonian Swan Hills Formation, Leduc Formation and Wabamun Group contain replacement dolomite (RD) cross‐cut by stylolites, suggesting replacement dolomitization occurred during shallow burial. Stable isotope, REE+Y and ⁸⁷Sr/⁸⁶Sr data indicate RD formed from Devonian seawater, then recrystallized during burial. Apart from the Wabamun Group of the Peace River Arch (PRA), saddle dolomite cement (SDC) is more δ¹⁸O_(PDB) depleted than RD, and cross‐cuts stylolites, suggesting precipitation during deep burial. SDC ⁸⁷Sr/⁸⁶Sr data indicate contributions from ⁸⁷Sr‐rich basinal brines in the West Shale Basin (WSB) and PRA, and authigenic quartz/albite suggests basinal brines interacted with underlying clastic aquifers before ascending faults into carbonate strata. The absence of quartz/albite within dolomites of the East Shale Basin (ESB) suggests dolomitizing fluids only interacted with carbonate strata. We conclude that replacement dolomitization resulted from connate Devonian seawater circulating through aquifers and faults during shallow burial. SDC precipitated during deep burial from basinal brines sourced from basal carbonates (ESB) and clastic aquifers (WSB, PRA). Lithium‐rich formation waters suggest basinal brines originated as residual evapo‐concentrated Middle Devonian seawater that interacted with basal aquifers and ascended faults during the Antler and Laramide Orogenies. These results corroborate those of previous studies but are verified by new integrated analysis of multiple datasets. New insights emphasize the importance of basal aquifers and residual evapo‐concentrated seawater in dolomitization, which is potentially applicable to other regionally dolomitized basins.

Deep learning architectures have transformed data analytics in geosciences, complementing traditional approaches to geological problems. Although deep learning applications in geosciences show encouraging signs, their potential remains untapped due to limited data availability and the required in-depth knowledge to provide a high-quality labeled dataset. We approached these issues by developing a novel style-based deep generative adversarial network (GAN) model, PetroGAN, to create the first realistic synthetic petrographic datasets across different rock types. PetroGAN adopts the architecture of StyleGAN2 with adaptive discriminator augmentation (ADA) to allow robust replication of statistical and esthetical characteristics and improve the internal variance of petrographic data. In this study, the training dataset consists of > 10,000 thin section images both under plane- and cross-polarized lights. Here, using our proposed novel approach, the model reached a state-of-the-art Fréchet Inception Distance (FID) score of 12.49 for petrographic images. We further observed that the FID values vary with lithology type and image resolution. The generated images were validated through a survey where the participants have various backgrounds and level of expertise in geosciences. The survey established that even a subject matter expert observed the generated images were indistinguishable from real images. This study highlights that GANs are a powerful method for generating realistic synthetic data in geosciences. Moreover, they are a future tool for image self-labeling, reducing the effort in producing big, high-quality labeled geoscience datasets. Furthermore, our study shows that PetroGAN can be applied to other geoscience datasets, opening new research horizons in the application of deep learning to various fields in geosciences, particularly with the presence of limited datasets.

The North Sea sedimentary basin is characterized by geological complexity, encompassing a wide range of rock types and structures, including multiple reservoirs (carbonates and siliciclastic) with variations in reservoir quality and heterogeneity. These phenomena pose significant challenges for accurately predicting reservoir properties using traditional well log analysis. Moreover, these challenges are further compounded by complex geological conditions and scarcity of available data. Hence, the aim of this study was to address these challenges by applying advanced machine learning techniques within this basin. This study delves into both supervised and unsupervised machine learning approaches to forecast the essential petrophysical properties that are crucial for assessing reservoir quality. These properties encompass total porosity, effective porosity, and shale volume, all derived from well log data originating from the North Sea sedimentary basin. The models were trained using data from four wells consisting of 32,215 data points (80% for training, 10% for testing, and 10% for validation). Furthermore, our study introduced pioneering data-driven preprocessing workflow, encompassing exploratory data analysis, missing data imputation, and outlier detection to improve the performance of the machine learning models. ANN and RF models achieved the best results among the algorithms evaluated, with an average MAE of 0.01, RMSE of 0.01, and R-squared of 0.95 for total porosity, effective porosity, and volume of shale, respectively. These metrics demonstrate that the model can accurately predict reservoir properties in a challenging sedimentary basin, even with limited data availability, enabling reservoir characteristics and field development optimization, particularly in areas where core data are scarce.

The early Miocene Wadi Waqb carbonate in the Midyan Peninsula, NE Red Sea is of great interest not only because of its importance as an archive of one of the few pre-salt synrift carbonate platforms in the world, but also as a major hydrocarbon reservoir. Despite this importance, little is known about the diagenesis and heterogeneity of this succession. This study uses petrographical, elemental chemistry, stable isotope (δ ¹³ C and δ ¹⁸ O) and clumped isotope (Δ ₄₇ ) analyses to decipher the controlling processes behind the formation of various diagenetic products, especially dolomite, from two locations (Wadi Waqb and Ad-Dubaybah) that have experienced different diagenetic histories. Petrographically, the dolomites in both locations are similar, and characterized by euhedral to subhedral crystals (50–200 µm) and fabric-preserving dolomite textures. Clumped isotope analysis suggests that slightly elevated temperatures were recorded in the Ad-Dubaybah location (up to 49°C), whereas the Wadi Waqb location shows a sea-surface temperature of c. 30°C. These temperature differences, coupled with distinct δ ¹⁸ O _VPDB values, can be used to infer the chemistry of the fluids involved in the dolomitization processes, with fluids at the Wadi Waqb location displaying much higher δ ¹⁸ O _SMOW values (up to +4‰) compared to those at the Ad Dubaybah location (up to −3‰). Two different dolomitization models are proposed for the two sites: a seepage reflux, evaporative seawater mechanism at the Wadi Waqb location; and a fault-controlled, modified seawater mechanism at the Ad-Dubaybah location. At Ad-Dubaybah, seawater was modified through interaction with the immature basal sandstone aquifer, the Al-Wajh Formation. The spatial distribution of the dolostone bodies formed at these two locations also supports the models proposed here: with the Wadi Waqb location exhibiting massive dolostone bodies, while the dolostone bodies in the Ad-Dubaybah location are mostly clustered along the slope and platform margin. Porosity is highest in the slope sediments due to the interplay between higher precursor porosity, the grain size of the original limestone and dolomitization. Ultimately, this study provides insights into the prediction of carbonate diagenesis in an active tectonic basin and the resultant porosity distribution of a pre-salt carbonate reservoir system.