In the past, reservoir engineers used numerical simulation or reservoir engineering methods to predict oil production, and the accuracy of prediction depended more on the engineers’ own experience. With the development of data science, a new trend has arisen to use deep learning to predict oil production from the perspective of data. In this study, a hybrid forecasting model (CNN-LSTM) based on a convolutional neural network (CNN) and a Long Short-Term Memory (LSTM) neural network is proposed and used to predict the production of fractured horizontal wells in volcanic reservoirs. The model solves the limitation of traditional methods that rely on personal experience. First, the production constraints and production data are used to form a feature space, and the abstract semantics of the feature time series are extracted through convolutional neural network, then the LSTM neural network is used to predict the time series. The certain hyperparameters of the whole model are optimized by Particle Swarm Optimization algorithm (PSO). In order to estimate the model, some production dynamics from the Xinjiang oilfield of China are used for comparative analysis. The experimental results show that the CNN-LSTM model is superior to traditional neural networks and conventional decline curves.

Most of the oil reservoirs in China are fluvial deposits with firm reservoir heterogeneity, where differences in fluid flow capacity in individual directions should not be ignored; however, the available commercial reservoir simulation software cannot consider the anisotropy of the relative permeability. To handle this challenge, this paper takes full advantage of the parallelism of the multi-scale finite volume (MsFV) method and establishes a multi-scale numerical simulation approach that incorporates the effects of reservoir anisotropy. The methodology is initiated by constructing an oil–water black-oil model considering the anisotropic relative permeability. Subsequently, the base model undergoes decoupling through a sequential solution, formulating the pressure and transport equations. Following this, a multi-scale grid system is configured, within which the pressure and transport equations are progressively developed in the fine-scale grid domain. Ultimately, the improved multi-scale finite volume (IMsFV) method is applied to mitigate low-frequency error in the coarse-scale grid, thereby enhancing computational efficiency. This paper introduces two primary innovations. The first is the development of a multi-scale solution method for the pressure equation incorporating anisotropic relative permeability. Validated using the Egg model, a comparative analysis with traditional numerical simulations demonstrates a significant improvement in computational speed without sacrificing accuracy. The second innovation involves applying the multi-scale framework to investigate the impact of anisotropy relative permeability on waterflooding performance, uncovering distinct mechanisms by which absolute and relative permeability anisotropy influence waterflooding outcomes. Therefore, the IMsFV method can be used as an effective tool for high-resolution simulation and precise residual oil prediction in anisotropic reservoirs.

Tight oil reservoirs offer significant development potential. Due to the pronounced capillary forces in their nanopores, phase behavior differs markedly from that in conventional reservoirs, challenging traditional equations of state and numerical simulation methods. This paper presents a multiscale compositional numerical simulation method that incorporates capillary forces, leveraging the parallel advantages of the multiscale finite volume method. The approach decouples the compositional model using a sequential format to derive pressure and transport equations, then solves the pressure equation iteratively in a multiscale format to enhance computational efficiency. Results show that the proposed method significantly improves simulation speed while maintaining accuracy. By considering capillary forces in phase equilibrium calculations, this model effectively characterizes phase behavior in tight oil reservoir development, making it highly relevant for Pressure Volume Temperature (PVT) simulation, development simulation, and forecasting development strategies.

Multi-fractured horizontal well (MFHW) technology is a key technology for developing unconventional reservoirs, which can generate a complex fracture network called a stimulated reservoir volume (SRV). Currently, there are many relative analytical models to describe the fluid seepage law, which are not suitable for volcanic reservoirs as of yet. The reasons are as follows: (1) due to the development of natural fractures, multi-scaled flow (matrix, natural fractures, SRV) should be considered to characterize MFHW flow in volcanic reservoirs; (2) non-Darcy flow and stress sensitivity should be considered simultaneously for seepage in volcanic reservoirs. Thus, this paper presents a novel MFHW analysis model of volcanic reservoirs that uses a multi-scale dual-porosity medium model and complex flow mechanisms. Laplace transformation, the Duhamel principle, the perturbation method and Stehfest numerical inversion are employed to solve the model to obtain dynamic pressure response curves. The results show that the pressure response curve can be divided into eight stages. Sensitivity analysis shows that the parameters of hydraulic fractures mainly affect the early flow stage. The parameters of the SRV region mainly affect the middle flow stage. The parameters of unreconstructed regions, non-Darcy flow and stress sensitivity mainly affect the late flow stage.