As terrestrial oilfields continue to be explored, the difficulty of exploring new oilfields is constantly increasing. The ocean, which contains abundant oil and gas resources, has become a new field for oil and gas resource development. It is estimated that the total amount of oil resources contained in ocean areas accounts for 33% of the global total, while the corresponding natural gas resources account for 32% of the world’s resources. Current prediction methods, tailored to land oilfields, struggle with offshore differences, hindering accurate forecasts. With oilfield advancements, a vast amount of rapidly generated, complex, and valuable data has piled up. This paper uses AI and GRN-VSN NN to predict offshore oilfield indicators, focusing on model-based formula fitting. It selects highly correlated input indicators for AI-driven prediction of key development metrics. Afterwards, the Shapley additive explanations (SHAP) method was introduced to explain the artificial intelligence model and achieve a reasonable explanation of the measurement’s results. In terms of crude-oil extraction degree, the performance levels of the Long Short-Term Memory (LSTM) neural network, BP neural network, and ResNet-50 neural network are compared. LSTM excels in crude-oil extraction prediction due to its monotonicity, enabling continuous time-series forecasting. Artificial intelligence algorithms have good prediction effects on key development indicators of offshore oilfields, and the prediction accuracy exceeds 92%. The SHAP algorithm offers a rationale for AI model parameters, quantifying input indicators’ contributions to outputs.

Summary: Gas permeability in hydrate reservoirs is the decisive parameter in determining the gas production efficiency and gas production of hydrate. In the South China Sea (SCS), the gas flow in tight natural gas hydrate (NGH) silty clay reservoirs is significantly affected by the gas slippage effect and the effective stress (ES) of overlying rock. To improve the effectiveness of hydrate exploitation, it is necessary to understand the influence of gas slippage in hydrate reservoirs on the permeability evolution law. For this paper, the gas permeability characteristics and methane production of hydrate montmorillonite sediments were studied at different pore pressures and ESs. Experimental data revealed that the gas permeability of montmorillonite samples before methane hydrate (MH) formation is seriously affected by the Klinkenberg effect. The gas permeability of montmorillonite sediments before hydrate formation is generally smaller than that after hydrate formation, and the gas slippage effect in the sediments after hydrate formation is weaker than that before hydrate formation. With the change in ES, the intrinsic permeability of sediment has a power law relationship with the simple ES. The ES law coefficient n was determined using the response surface method to eliminate the influence of gas slip on gas permeability. As pore pressure decreases and MH decomposes, montmorillonite swelling seriously affects gas permeability. However, the gas slippage effect has a good compensation effect on the permeability of montmorillonite sediments after MH decomposition under low pore pressure. The multistage depressurization-producing process of MH in montmorillonite sediments is mainly 3 MPa depressurization-producing stage and 2 MPa depressurization-producing stage. In this paper, the influence mechanism of gas slippage effect of hydrate reservoir is studied, which is conducive to improving the prediction accuracy of gas content in the process of hydrate exploitation and exploring the best pressure reduction method to increase the gas production of hydrate in the process of exploitation.

This research explores the geomechanical challenges associated with gas hydrate extraction in submarine slope zones, a setting posing a high risk of significant geological calamities. We investigate slope and wellbore deformations driven by hydrate decomposition within a subsea environment. Utilizing Abaqus, a fluid-solid-thermal multi-field coupling model for gas hydrate reservoirs was created. Hydrate decomposition during drilling is minimal, resulting in minor formation deformation near the wellbore. However, a year of hydrate production caused a maximum displacement of up to 7 m in the wellbore and formation, highlighting the risk of submarine landslides. This indicates the need for meticulous surveillance of formation subsidence and wellhead equipment displacement. In the aftermath of a hydrate-induced submarine landslide, both the hydrate layer and the overlying strata descend together, inflicting considerable damage on the formation and wellbore. Our study presents a holistic examination of the interplay between environmental geomechanics risks and engineering structure risks for submarine slope instability and wellbore stability during hydrate development, providing crucial insights for enhancing safety measures in hydrate drilling and production, and ensuring wellbore stability.

This paper demonstrates the applicability of machine learning algorithms in sand production problems with natural gas hydrate (NGH)-bearing sands, which have been regarded as a grave concern for commercialization. The sanding problem hinders the commercial exploration of NGH reservoirs. The common sand production prediction methods need assumptions for complicated mathematical derivations. The main contribution of this paper was to introduce machine learning into the prediction sand production by using data from laboratory experiments. Four main machine learning algorithms were selected, namely, K-Nearest Neighbor, Support Vector Regression, Boosting Tree, and Multi-Layer Perceptron. Training datasets for machine learning were collected from a sand production experiment. The experiment considered both the geological parameters and the sand control effect. The machine learning algorithms were mainly evaluated according to their mean absolute error and coefficient of determination. The evaluation results showed that the most accurate results under the given conditions were from the Boosting Tree algorithm, while the K-Nearest Neighbor had the worst prediction performance. Considering an ensemble prediction model, the Support Vector Regression and Multi-Layer Perceptron could also be applied for the prediction of sand production. The tuning process revealed that the Gaussian kernel was the proper kernel function for improving the prediction performance of SVR. In addition, the best parameters for both the Boosting Tree and Multi-Layer Perceptron were recommended for the accurate prediction of sand production. This paper also involved one case study to compare the prediction results of the machine learning models and classic numerical simulation, which showed the capability of machine learning of accurately predicting sand production, especially under stable pressure conditions.

The leakage process simulation of a Natural Gas Liquid (NGL) storage tank requires the simultaneous solution of the NGL’s pressure, temperature and phase state in the tank and across the leak hole. The methods available in the literature rarely consider the liquid/vapor phase transition of the NGL during such a process. This paper provides a comprehensive pressure-temperature-phase state method to solve this problem. With this method, the phase state of the NGL is predicted by a thermodynamic model based on the volume translated Peng-Robinson equation of state (VTPR EOS). The tank’s pressure and temperature are simulated according to the pressure-volume-temperature and isenthalpic expansion principles of the NGL. The pressure, temperature, leakage mass flow rate across the leak hole are calculated from an improved Homogeneous Non-Equilibrium Diener-Schmidt (HNE-DS) model and the isentropic expansion principle. In particular, the improved HNE-DS model removes the ideal gas assumption used in the original HNE-DS model by using a new compressibility factor developed from the VTPR EOS to replace the original one derived from the Clausius-Clayperon equation. Finally, a robust procedure of simultaneously solving the tank model and the leak hole model is proposed and the method is validated by experimental data. A variety of leakage cases demonstrates that this method is effective in simulating the dynamic leakage process of NGL tanks under critical and subcritical releasing conditions associated with vapor/liquid phase change.

The application of hole cleaning devices can effectively solve the hole cleaning problem during the drilling of horizontal wells. Improving the hole cleaning performance is directly related to subsequent drilling time and cost. In this paper, the solid–liquid two-phase hydrodynamic characteristics under the action of the V-shaped hole cleaning device for drilling horizontal wells were studied experimentally and numerically. The decay law of spiral flow induced by the V-shaped hole cleaning device was obtained numerically using the commercial CFD code “Fluent” by changing the blade rotational speed, blade helix angle, and consistency coefficient of drilling fluid. The helix angle will cause the flow direction of local fluid to deflect. The swirl intensity of spiral flow increases significantly with an increase in rotational speed. The hole cleaning performance was better when the helix angle was from about 10 to 20 degrees. Increasing the fluid consistency coefficient will rapidly make the spiral flow decay, resulting in a shorter effective action distance and a worse hole cleaning effect. The simulation results were validated against the experimental results of the flow loop. Both experimental and simulation results showed that the hole cleaning performance was improved by using the V-shaped hole cleaning device. The very good agreement achieved between the results has presented an opportunity to study the hole cleaning effect of a hole cleaning device in unsteady state conditions. The results will provide theoretical guidance for efficient hole cleaning using V-shaped hole cleaning devices for horizontal well drilling.