This paper evaluated the oil and gas potential of the Cretaceous Yageliemu clastic reservoir within the Yakela condensed gas field lying in the Kuqa Depression, Tarim Basin, China. The petrophysical properties of the interest zones in the Kuqa area were characterized using geophysical logs from five wells. The results reveal that the gas-bearing zones are characterized by high resistivity, good permeability (K) and effective porosity (Φeff), low water saturation (Sw), and low shale concentration (Vsh), reflecting clean sand. The shale distribution model showed that these shales have no major influence on porosity and fluid saturation. The average shale volume, average effective porosity, and hydrocarbon saturation indicate that the Cretaceous Yageliemu Formation in the studied area contains prospective reservoir properties. The spatial distribution of petrophysical parameters, reservoir rock typing (RRT), and lithofacies were analyzed using the cross plots of litho saturation (volumetric analysis), iso-parametric representations of the petrophysical characteristics, cluster analysis, and self-organizing feature maps, respectively. The southeastern and northeastern regions of the research area should be ignored because of their high water and shale concentrations. The sediments in the southwest and northwest include the most potential reservoir intervals that should be considered for the future exploration and development of oil and gas fields in the study area.

The precise characterization of geological bodies in fracture-vuggy carbonates is challenging due to their high complexity and heterogeneous distribution. This study aims to present the hybrid of Visual Geometry Group 16 (VGG-16) pre-trained by Gradient-Boosting Decision Tree (GBDT) models as a novel approach for predicting and generating karst cavities with high accuracy on various scales based on uncertainty assessment from a small dataset. Seismic wave impedance images were used as input data. Their manual interpretation was used to build GBDT classifiers for Light Gradient-Boosting Machine (LightGBM) and Unbiased Boosting with Categorical Features (CatBoost) for predicting the karst cavities and unconformities. The results show that the LightGBM was the best GBDT classifier, which performed excellently in karst cavity interpretation, giving an F1-score between 0.87 and 0.94 and a micro-G-Mean ranging from 0.92 to 0.96. Furthermore, the LightGBM performed better in cave prediction than Linear Regression (LR) and Multilayer Perceptron (MLP). The prediction of karst cavities according to the LightGBM model was performed well according to the uncertainty quantification. Therefore, the hybrid VGG16 and GBDT algorithms can be implemented as an improved approach for efficiently identifying geological features within similar reservoirs worldwide.

In China, Tahe Triassic oil field block 9 reservoir was discovered in 2002 by drilling wells S95 and S100. The distribution of the reservoir sand body is not clear. Therefore, it is necessary to study and to predict oil production from this oil field. In this study, we propose an improved Random Vector Functional Link (RVFL) network to predict oil production from Tahe oil field in China. The Spherical Search Optimizer (SSO) is applied to optimize the RVFL and to enhance its performance, where SSO works as a local search method that improved the parameters of the RVFL. We used a historical dataset of this oil field from 2002 to 2014 collected by a local partner. Our proposed model, called SSO-RVFL, has been evaluated with extensive comparisons to several optimization methods. The outcomes showed that, SSO-RVFL achieved accurate predictions and the SSO outperformed several optimization methods.

The Cretaceous condensate gas reservoir in Yakela is in a fan delta system in which the river channel swings frequently and the contact relationships between sandbodies are complicated both vertically and horizontally. Therefore, making the sandbody architecture clear is becoming the most urgent demand in locating the remaining oil. However, conventional well correlations and fine interpretation do not apply in this area due to the large-spacing of wells and the lack of reliable seismic data. In this paper, we analyzed the vertical characteristics of sandbody architecture including the type and thickness of architectural elements and their contact relationships based on well data, then simulated the lateral and planar distribution probabilities via a database containing a large number of dimension parameters from relevant architectural elements using Monte Carlo simulation. This simulation provides reasonable and efficient estimation of inter-well sandbody distribution. The workflow and data we present can be applied to similar clastic reservoir modeling and simulations, especially for areas with insufficient well and seismic data.