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.

Most multilayer sandstone reservoirs in the Bohai Sea have already entered the middle or high water cut production stage with large amounts of remaining oil being scattered distributed. Therefore, there is an urgent need to find a suitable countermeasure to reduce water cut and increase oil recovery. In this study, taking the narrow-channel reservoirs in the M oilfield as an example, we qualitatively described the sand body scale and the contact relationships between different sand bodies, in addition to carefully analyzing the material base and remaining oil distribution characteristics. Accordingly, we proposed a countermeasure based on the injection-production structural adjustment to reduce water cut and increase oil recovery from high water cut, narrow-channel reservoirs. Herein, three optimization strategies were developed based on the proposed development mode: a seepage field optimization strategy was developed based on the quantified injection-production index; a well pattern optimization strategy for narrow-channel reservoirs was developed to overcome the production energy refueling problem; an injection-production measure optimization strategy was developed to tap the different types of remaining oil. Additionally, the well pattern optimization and injection-production optimization strategies were integrated to optimize and adjust the seepage field system. The findings reported herein this paper help understand the development of similar offshore oilfields with a high water cut.

Steam flooding is one of the most effective and mature technology in heavy oil development. In this paper, a numerical simulation technology of steam flooding reservoir based on the finite volume method is firstly established. Combined with the phase change of steam phase, the fully implicit solution for steam flooding is carried out by using adaptive-time-step Newton iteration method. The Kriging method is used for stochastically to generate 4250 geological model samples by considering reservoir heterogeneity, and corresponding production schedule parameters are randomly given; then, these reservoir model samples are handled by the numerical simulation technology to obtain corresponding dynamic production data, which constitute the data for artificial neural network (ANN) training. By using the highly nonlinear global effect of artificial neural network and its powerful self-adaptive and self-learning functions, the forward-looking and inverse design ANN models of steam-flooding reservoirs are established, which provides a new method for rapid prediction of steam-flooding production performance and production schedule parameter design. In 4250 samples, the error of the forward-looking model is basically less than 0.1%, and the error of the inverse design model is generally less than 15%. It fully shows that the ANN models developed in this paper can quickly and effectively predict oil production and design production parameters and have an important guiding role in the implementation of the steam flooding technology. Finally, the forward-looking ANN model is applied to efficiently analyze the influencing factors of steam flooding process, and uncertainty analysis of the inverse design ANN model is conducted by Monte Carlo Simulation to illustrate its robustness. Besides, this paper may provide a reference for the application of neural network models to underground oil and gas reservoir, which is a typical invisible black box.

Fault-karst reservoirs are featured by complex geological characteristics, and accurate and fast simulation of such kind of reservoirs using traditional simulator and simulation methods is pretty hard. Herein, we tried to discrete the complex fault-karst structures into one-dimensional connected units connecting the well, fracture and cave based on reservoir static physical parameters and injection-production dynamics. Two characteristic parameters, conductivity and connected volume, are proposed to characterize the inter-well connectivity and material basis. Meanwhile, the high-speed non-Darcy seepage term is introduced into the material balance equations for well-fracture-cave connected units to describe the actual seepage characteristics within the fault-karst reservoirs, and to better simulate the oil/water production dynamics. Based on this method, a fracture reservoir model of 1 injection-3 production was established. The change of oil–water action law in different injection and extraction systems under two production regimes of fixed production rate and fixed pressure is analyzed. A case study was conducted on S fault zone, where the flow of oil and gas did not follow the Darcy seepage rule and with a β value of 10³–10⁴, the single well flow pressure and oil production were perfectly matched with the real data. In addition, connected units with more prominent high-speed non-Darcy features were found to have better connectivity, which might shed light on the more accurate prediction of inter-well connectivity. Moreover, an improved injection-production well pattern and was proposed based on connectivity prediction model and reservoir engineering method to solve the problems of insufficient natural energy supply and overhigh oil production rate in Block S. Furthermore, the injection/production rate as well as the timing and cycle of water injection was predicted and optimized so as to better guide to site operations.

Progress and Enlightenment of Refracturing Technology for Shale Gas in North America