Re-Calibration of Empirical PVT Correlations for Crude Oil Formation Volume Factor Using Non-Linear Optimization Algorithms

Development and Validation of an Empirical Correlation for Water Production Forecasting in Petroleum Reservoirs

Accurate water production prediction is critical for field development optimization, surface facility design, and production management in mature oil reservoirs. This study develops empirical correlations for forecasting Water-Oil Ratio (WOR) using 9,161 production records from seven Volve Field wells (Norwegian North Sea, 2007–2016). Four approaches were evaluated: multiple linear regression, power law correlation, polynomial regression, and an exponential model, benchmarked against established methods including the X-Plot, Ershaghi-Omoregie, Buckley-Leverett, Arps decline curve, and Chan diagnostic techniques. Feature engineering generated derived variables including cumulative oil production, pressure ratio, production time, gas-oil ratio, and productivity index. After removing non-physical values and treating extreme WOR observations, data were split 80/20 for training and validation. The power law correlation achieved the strongest test-set performance (R2 = 0.845, RMSE = 2.374, MAE = 1.065), expressing WOR as a function of cumulative oil production, pressure ratio, and production time. It outperformed all conventional benchmarks, with the Arps decline-based method representing the best traditional comparator but at substantially lower accuracy. These results demonstrate that simple empirical correlations, when derived from high-quality datasets, can reliably forecast water production behavior. The proposed correlation provides a practical, easily implemented tool for production forecasting, water handling capacity planning, and operational decision-making within standard reservoir engineering workflows.

Economic benefit forecasting and parametric sensitivity analysis for shallow shale gas wells in the Zhaotong area using machine learning

In shale gas development, Net Present Value (NPV) and Internal Rate of Return (IRR) are influenced by the coupling of multi-source geological and engineering parameters, and quantitative research on the marginal effects and risk thresholds of key parameters remains lacking. A deep feedforward neural network prediction model was constructed to achieve mapping from 19-dimensional features to NPV and IRR. The trained model was then utilized as a digital surrogate model to conduct univariate sensitivity analysis, quantifying the marginal impacts of parameters such as clay content, carbonate content, effective porosity, Poisson’s ratio, horizontal stress difference, and first-year average daily production on economic benefits. Cross-validated results indicate that the model achieves a mean R 2 of 0.6071 (±0.0957) for NPV prediction and 0.4168 (±0.1294) for IRR prediction. Furthermore, it identifies economic risk thresholds including 30% for clay content, 0.2 for Poisson’s ratio, and 17 MPa for horizontal stress difference, which are highly consistent with oilfield engineering experience. SHAP-based interaction analysis reveals that these thresholds are context-dependent, with interaction effects accounting for approximately 30%–32% of the main effects for clay content and horizontal stress difference.

Efficient optimization of offshore natural gas dehydration processes based on data-driven approaches

Correlation-Based Estimation of Condensate Yield from Downhole Fluid Gradient

Evaluation of investment opportunities in gas developments requires comprehensive subsurface data analysis and integration to quantify both value potential and associated risks. A critical element in such evaluations is the estimation of condensate yield, expressed as the Condensate–Gas Ratio (CGR), which supports the determination of condensate initially in place (CIIP) and forecasted condensate recoveries under different development scenarios. Although gas volumes typically dominate in such systems, the associated condensate liquids often provide a significant value upside, particularly under Nigeria's favorable natural gas liquids (NGL) fiscal regimes. During due diligence on a new gas asset, neutron–density log responses exhibited ballooning behavior consistent with a gas phase. This interpretation was corroborated by Repeat Formation Tester (RFT) pressure gradients of less than 0.18 psi/ft, as well as by seismic attribute analysis that also indicated gas-bearing intervals. However, the absence of bottomhole or recombined surface PVT data and Drill Stem Test (DST) results posed a challenge for estimating the fluid's condensate yield, a critical parameter for project evaluation. To address this data gap, a comprehensive corporate database of retrograde gas reservoirs with laboratory PVT analyses and RFT/MDT fluid gradient data was utilized. Empirical correlations were developed by trending measured fluid gradients against known laboratory-determined CGRs. The derived correlation was subsequently applied to the new opportunity, using its measured gradients to estimate the CGRs for the respective reservoirs. The accuracy of the developed correlation was tested against MDT and PVT data from a condensate reservoir in a recently drilled well and the resulting CGR estimate lies within <5% variance from that measured in the lab. These estimates were then integrated into PVT correlations and dynamic material balance models to compute condensate initially in place and evaluate development scenarios. The correlation-based approach provided reliable CGR estimates in the absence of direct PVT measurements and delivered a significant fiscal uplift to the project's overall economics. The study demonstrates that gradient-based empirical correlations, when supported by robust internal datasets, can effectively reduce uncertainty in condensate yield estimation and enhance investment decision-making in gas and condensate projects.

Data-Driven Modelling of Oil Flow Rates in Vertical Wells: Performance Comparisons of Neural Network and Multigene Genetic Programming Approaches

Accurate prediction of oil production rates remains challenging, especially in fields where direct measurement is not feasible. To address this issue, data-driven models were developed using neural networks (NN) and multigene genetic programming (MGGP) to provide real-time estimations of oil flow rates in vertical wells using routinely measured field parameters. The models were trained and tested on 70% and 30% of a dataset comprising 1,893 entries, respectively. The input variables for the models include oil API gravity, downstream temperature, upstream temperature, upstream pressure, and choke size. These developed models are simplified, reproducible, and suitable for practical application. Model performance was quantitatively evaluated using the correlation coefficient (R), the coefficient of determination (R2), the mean squared error (MSE), and the root mean square error (RMSE). The NN model demonstrated superior predictive capability, achieving R = 0.990, R2 = 0.980, MSE = 0.0001, and RMSE = 0.011, while the MGGP model achieved R = 0.980, R2 = 0.960, MSE = 0.0004, and RMSE = 0.020. Validation using an independent dataset further confirmed the robustness of the NN model, which outperformed the MGGP model across all evaluation metrics. Additional contributions of this study include sensitivity analysis of input variables, derivation of explicit predictive correlations, and evaluation of computational efficiency. Both models exhibited low computational cost, supporting real-time and field-scale applicability. Thus, the NN model outperforms the MGGP model in estimating oil field flow rates. Therefore, production engineers are recommended to utilise an NN-based model as a decision-support tool for estimating oil flow in vertically flowing wells.

Methods for Risk Assessment of Inorganic Scaling in Crude Oil–Water Transport Trunklines Connected by Multiple Production Flowlines: A Comprehensive Literature Review

Inorganic scale deposition in crude oil–water transport trunklines is a formidable flow assurance challenge, uniquely exacerbated in extensive gathering networks where multiple production flowlines commingle multiphase fluids. As some fields experience progressively higher water cuts, the mixing of incompatible waters, characterized by diverse thermodynamic profiles and varying concentrations of scaling ions (Ca2+, Ba2+, Sr2+, SO42−, CO32−, etc.) triggers severe precipitation. This comprehensive literature review synthesizes seminal and contemporary studies to critically evaluate the state-of-the-art methodologies for assessing scaling risks in these intricate systems. Progressing chronologically and thematically, the analysis details the transition from static, bulk-fluid thermodynamic equilibrium calculations to dynamic, high-fidelity deterministic and probabilistic approaches. These advanced frameworks include Reactive Transport Modeling (RTM), Computational Fluid Dynamics (CFD), and Machine Learning (ML) architectures. Special emphasis is placed on the mathematical governing equations that dictate trunkline-specific phenomena: multi-stream commingling, non-isothermal gradients, probabilistic kinetic induction, and the profound impact of turbulent transport (turbophoresis) on crystal attachment and wall shear detachment. Finally, an integrated, multi-tier flow assurance workflow is proposed to guide future field-scale risk management and digital twin deployment.