Search

Lithofacies identification and classification are critical for characterizing the hydrocarbon potential of unconventional resources. Although extensive applications of machine learning models in predicting lithofacies have been applied to conventional reservoir systems, the effectiveness of machine learning models in predicting clay-rich, lacustrine shale lithofacies has yet to be tackled. Here, we apply machine learning models to conventional well log data to automatically identify the shale lithofacies of Gulong Shale in the Songliao Basin. The shale lithofacies were classified into six types based on total organic carbon and mineral composition data from core analysis and geochemical logs. We compared the accuracy of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest models. We mitigated the bias of imbalanced data by applying oversampling algorithms. Our results show that ensemble methods (XGBoost and Random Forest) have a better performance in shale lithofacies identification than the other models do, with accuracies of 0.868 and 0.884, respectively. The organic siliceous shale proposed to have the best hydrocarbon potential in Gulong Shale can be identified with F1 scores of 0.853 by XGBoost and 0.877 by Random Forest. Our study suggests that ensemble machine learning models can effectively identify the lithofacies of clay-rich shale from conventional well logs, providing insight into the sweet spot prediction of unconventional reservoirs. Further improvements in model performances can be achieved by adding domain knowledge and employing advanced well log data.

Predicting the spatial distribution of braided fluvial facies reservoirs is of paramount significance for oil and gas exploration and development. Given that seismic materials enjoy an advantage in dense spatial sampling, many methods have been proposed to predict the reservoir distribution based on different seismic attributes. Nevertheless, different seismic attributes have different sensitivities to the reservoirs, and informational redundancy between them makes it difficult to combine them effectively. Regarding reservoir modeling, multi-point geostatistics represents the distribution characteristics of the braided fluvial facies reservoirs effectively. Despite this, it is very difficult to build high-quality training images. Hence, this paper proposes a three-step method of predicting braided fluvial facies reservoirs based on probability fusion and multi-point geostatistics. Firstly, similar statistical data of modern sedimentation and field paleo-outcrops were processed under the guidance of the sedimentation pattern to construct reservoir training images suitable for the target stratum in the research area. Secondly, each linear combination of selected seismic attributes was demarcated to calculate the principal component value and work out the elementary conditional probability. Lastly, the PR probability integration approach was employed to combine all conditional probabilities and calculate the joint probability. Then the joint probability was combined with training images to build a reservoir distribution model through multi-point geostatistics. We illustrated the detailed workflow of our new method by applying it to a braided fluvial reservoir modeling case in the Bohai Bay Basin, East China. The new method reduced the error of prediction results by 32% and 46% respectively, and the error of water content by 36.5% and 60.3%. This method is a potentially effective technique to predict and characterize the reservoir spatial distribution and modeling in other oil fields with the same geological background.

Iterative geostatistical seismic inversion is a vital technique for estimating subsurface properties. However, a conventional single-scale strategy faces challenges in preserving large-scale geological features due to the limited restoration of the type of data template, and conventional multiscale strategies face the challenge in that it is easy to lose the large-scale structure that was previously preserved. This paper introduces a novel smoothed multiscale strategy aimed at overcoming these limitations, which comprises two components: Simulated annealing at the coarsest scale and smooth conversation between two scale grids. This approach offers a smoother way to simultaneously retain large-scale and small-scale structures, improving the overall accuracy of the subsurface property estimations. To validate the effectiveness of our approach, we apply it to both synthetic and real examples. The results show that the simulated annealing strategy at the coarsest scale grid explores the prior space and finds the best large structures to avoid the generated models trapping in the local minimal. Meanwhile, the smooth conversation strategy between two scale grids helps us avoid the damage of the coarser structure. It can be explained that a large weight is assigned to the coarse structure at the beginning of the conversation of two grid scale, reducing the likelihood of the replacing proposed local small-scale geological patterns, which prone to be accepted in the conventional multiscale strategies. The combination of the two strategies used in the proposed smoothed multiscale strategy displays a significant improvement in subsurface property estimation accuracy compared to traditional multiscale strategies. This innovation can have far-reaching implications, benefiting a wide range of geophysical applications and contributing to more accurate and informed decision-making in geological and hydrogeological assessments. [ABSTRACT FROM AUTHOR]

Studies reveal that the sea-surface temperature (SST) of the Northern Hemisphere decreased at a smaller amplitude than that of the Southern Hemisphere during the Eocene-Oligocene transition (EOT). This interhemispheric temperature asymmetry has been associated with intensified Atlantic Meridional Overturning Circulation (AMOC) that may have driven enhanced precipitation and weathering in low latitudes and the subsequent drawdown of atmospheric carbon dioxide. However, no quantitative constraints on paleo-precipitation have been reported in low latitudes to characterize the AMOC effect across the EOT. Here, we present the results of high-resolution (ca. 6 k.y. per sample) isotopic and biomarker records from the Gulf of Mexico. Reconstructed precipitation using leaf wax carbon isotopes shows an increase of 44% across the EOT (34.1-33.6 Ma), which is accompanied by a secular increase in SST of ~2 °C during the latest Eocene. We attribute the enhanced precipitation in the Gulf of Mexico to the northward shift of the Intertropical Convergence Zone that was driven by an enlarged polar-tropic temperature gradient in the Southern Hemisphere and an invigorated AMOC. Our findings link changes in meridional temperature gradient and large-scale oceanic circulation to the lowlatitude terrestrial hydroclimate and provide paleohydrological evidence that supports CO2-weathering feedback during the EOT "greenhouse" to "icehouse" transition. [ABSTRACT FROM AUTHOR]

The Qaidam Basin marks a crucial boundary between the Westerlies and the Asian summer monsoons. Previous studies in the Qaidam Basin have advanced our knowledge of the paleoclimate over glacial to interglacial cycles. However, our understanding of the paleoclimatic sensitivity of the Qaidam Basin to the relative strength of these two climatic driving forces remains limited due to the lack of regional paleoclimatic reconstructions. The Qaidam Basin is proposed as a regional and global eolian dust source during the glacial periods, during which a cold, dry climate is associated with the equatorward shift of the jet stream. On the contrary, paleoshoreline records suggest that a highstand lake stage prevailed in late Marine Isotope Stage 3 (MIS 3) and lasted until 15 ka. To address this conundrum, we have applied an integrated approach to reconstructing the regional paleoclimatic history by combining compound-specific isotope analysis, lake temperature reconstruction, and numerical modeling. Our results show varying paleoclimate associated with the dynamic climate boundary since 45 ka: (1) a wet climate during late MIS 3, when the Asian summer monsoons are strengthened under high summer insolation and penetrate further into Central Asia; (2) a general cold, dry but wetter than at present climate in the Last Glacial Maximum (LGM), when the Asian summer monsoons retreat and the Westerlies become dominant; and (3) three short periods of extreme aridity corresponding to the Younger Dryas and Heinrich 2 and 4 events, when the normal moisture transport via the Westerlies and Asian summer monsoons is interrupted. The numerical modeling supports an increase in the effective precipitation during the LGM due to reduced evaporation under low summer insolation. These results suggest that the Westerlies and Asian summer monsoons alternately controlled the climate in the Qaidam Basin in response to precessional forcing during the late Pleistocene. [ABSTRACT FROM AUTHOR]