A Novel Similarity-Based Upscaling Method for Highly Heterogeneous Reservoir Models

A Permeability Prediction Method for Tight Sandstone Reservoirs Based on XGBoost Algorithm

Permeability is a crucial parameter that characterizes the fluid migration capacity of reservoirs and is essential for hydrocarbon migration during accumulation and subsequent exploration and development. For tight sandstone reservoirs, the diverse pore types, complex pore-throat structures, and strong heterogeneity make it difficult to establish a stable correlation between porosity and permeability, thereby hindering accurate permeability prediction with conventional methods. To address this issue, this paper proposes a permeability prediction method based on an XGBoost (eXtreme Gradient Boosting) algorithm optimized with Optuna (an automatic hyperparameter optimization framework). The model’s accuracy, inter-well generalization ability, and interpretability are comprehensively evaluated by combining well-group validation, blind well independent verification, and SHapley Additive exPlanations (SHAP) global-local interpretation. Six characteristic parameters—core porosity (CORE-POR), natural gamma ray (GR), acoustic transit time (AC), compensated density (DEN), compensated neutron log (CNL), and photoelectric absorption cross-section index (PE)—are selected as input variables to construct the permeability prediction model. The predictive performance of the model was evaluated using the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The SHAP interpretation method was used to conduct global and local interpretability analysis of the model. The results show that Optuna-XGBoost outperforms multiple regression models and traditional machine-learning models on both the validation set and blind wells, indicating that this method is well-suited to permeability prediction for tight sandstone reservoirs in this study area.

Petrophysical and IPSOM Electrofacies Characterization of the Hartha Formation in Xn Oil Field, Central Iraq

Carbonate reservoirs of the Hartha Formation in central Iraq are characterized by significant heterogeneity, which poses challenges for accurate petrophysical evaluation. Traditional interpretation approaches often fail to adequately capture vertical and lateral variability in carbonate systems. The study presents a combination of conventional log interpretation and Interactive Petrophysics Self-organising Maps-based electrofacies classification to improve reservoir characterization and identify productive intervals. Wireline logs from wells EB-4, EB-52, and EBSZ-1 were subjected to quality control through depth matching, core-log calibration, and neutron-density crossplots. Petrophysical parameters were estimated using a carbonate workflow calibrated to core and SCAL data, with water saturation calculated using the Archie equation. Interactive Petrophysics Self-organising Maps electrofacies classification enabled effective reservoir zonation and differentiation between high and low quality intervals. The Hartha Formation shows strong vertical heterogeneity, with Ha-2 representing a low-quality water- bearing unit, while Ha3, particularly Ha3-c, forms the main reservoir unit with better porosity and lower water saturation. Net pay varies across the field, with EB-4 showing the highest values.  

ORIGINAL PAPER - EXPLORATION GEOLOGY

Optimization of Development Parameters for Tight Gas Reservoirs in Area S

The tight sandstone gas reservoirs in Area S are characterized by deep burial, strong heterogeneity, and poor petrophysical properties. Single-well productivity varies widely and declines rapidly; therefore, establishing optimal combinations of development parameters is essential for improving development efficiency. Taking the tight gas reservoir in Area S as the study object, this work integrates well logging, geological, and production dynamic data. A three-dimensional fine-scale geological model was constructed using sequential indicator simulation and sequential Gaussian simulation, and geological reserves were quantitatively evaluated using the Monte Carlo method (P50 = 4.818 × 109 m3). Based on this model, numerical simulation techniques were applied to conduct sensitivity analysis and optimization of key development parameters. The results indicate that for vertical wells in Area S, a reasonable fracture half-length ranges from 100 to 300 m with 3-4 fracturing stages; for horizontal wells, a reasonable lateral length ranges from 800 to 1000 m with a fracture half-length of approximately 100 m. For zones classified by reserve abundance, differentiated well-pattern layouts are proposed: a 900 m × 1200 m pattern for Class I zones, a 700 m × 1000 m pattern for Class II zones, and a 500 m × 700 m pattern for Class III zones. These findings provide a scientific basis and technical support for the efficient development of Area S and other similar tight gas reservoirs.

Integrated Well Log Petrophysical Analysis Using MATLAB for Reservoir Characterization in The Kujung Formation

This study aims to evaluate the reservoir potential and hydrocarbon prospectivity of the Kujung Formation using an integrated well log petrophysical analysis carried out through a MATLAB-based workflow. The methodology includes qualitative quicklook interpretation to identify hydrocarbon zones, the use of various crossplot methods for lithology characterization, and quantitative calculation of key petrophysical parameters. Log anomalies caused by tool sticking were excluded to ensure the reliability of the data. The qualitative evaluation indicates that the reservoir is mainly composed of clean limestone, with a shale layer above it acting as a seal rock. Quantitative analysis shows favorable reservoir properties within the 5,500–7,400 ft interval, with an average shale volume of 9.49%, an effective porosity of 14.34%, and a water saturation of 6.88%. By applying petrophysical cutoff limits, a net pay thickness of 1,251 ft was obtained from a gross interval of 1,700 ft. These results correspond to a net-to-gross ratio of 0.736. Overall, the findings suggest that the Kujung Formation acts as a productive gas reservoir.

A reduced order model framework suitable for geotechnical problems

Data-driven methods are of increasing popularity for solving problems in geotechnics, offering as they do, the possibility of high-fidelity results without the effort of a detailed deterministic numerical analysis (e.g. using finite elements). A wide range of approaches fall under the heading of Reduced Order Models (ROMs) which are created by processing data generated from high-fidelity models. The quality of these ROMs, and the computational cost of their construction, themselves depend heavily on the architecture chosen. In this study, we introduce a set of efficient frameworks for data-driven ROMs that can be applied to geotechnics problems in general. Our approach employs autoencoders and/or principal component analysis to reduce data dimensionality and to extract latent representations, followed by a Deep Operator Network (DeepONet) to learn nonlinear behaviour within this latent space. The architectures are demonstrated on the problem of the prediction of spatio-temporal responses in soil consolidation, and we demonstrate that the proposed efficient ROM architectures accurately predict responses for a range of problem specifications. The proposed framework provides a versatile methodology for large-scale complex geotechnical modelling applications.