Reservoir lithology identification is the basis for the exploration and development of complex lithological reservoirs. Efficient processing of well-logging data is the key to lithology identification. However, reservoir lithology identification through well-logging is still a challenge with conventional machine learning methods, such as Convolutional Neural Networks (CNN), and Long Short-term Memory (LSTM). To address this issue, a fully connected network (FCN) and LSTM were coupled for predicting reservoir lithology. The proposed algorithm (LSTM-FCN) is composed of two sections. One section uses FCN to extract the spatial properties, the other one captures feature selections by LSTM. Well-logging data from Hugoton Field is used to evaluate the performance. In this study, well-logging data, including Gamma-ray (GR), Resistivity (ILD_log10), Neutron-density porosity difference (DeltaPHI), Average neutron-density porosity(PHIND), and (Photoelectric effect) PE, are used for training and identifying lithology. For comparison, seven conventional methods are also proposed and trained, such as support vector machines (SVM), and random forest classifiers (RFC). The accuracy results indicate that the proposed architecture obtains better performance. After that, particle swarm optimization (PSO) is proposed to optimize hyper-parameters of LSTM-FCN. The investigation indicates the proposed PSO-LSTM-FCN model can enhance the performance of machine learning algorithms on identify the lithology of complex reservoirs.

Hydraulic fracturing is a crucial method in shale oil development, and predicting production after hydraulic fracturing is one of the challenges in shale oil development. Conventional methods for predicting production include analytical methods and numerical simulation methods, but these methods involve many parameters, have high uncertainty, and are time-consuming and costly. With the development of shale oil development, there are more and more sample data on the geological parameters, engineering parameters, and development parameters of shale oil hydraulic fracturing, making it possible to use machine learning methods to predict production after hydraulic fracturing. This article first analyzes the impact of different parameters on initial production and recoverable reserves based on field data from Chang-7 shale oil in the Ordos Basin of China. Then, using the Particle Swarm Optimization (PSO) algorithm and the Gradient Boosting Decision Tree (GBDT) algorithm, machine learning models for initial production and recoverable reserves are established. The Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) explanation methods are used to explain the models. The study found that initial production is highly correlated with parameters such as the number of fracturing stages and fracturing fluid volume, while recoverable reserves are significantly related to parameters such as well spacing, area, and reserver-controlled. The PSO-GBDT model established in this study has an accuracy of over 85% and can be used for production prediction and subsequent parameter optimization research. By comparing the LIME and SHAP local explanation methods, it is shown that different explanation methods can obtain reasonable and credible local explanation results. This article establishes a high-precision shale oil well production prediction model and two model interpretation methods, which could provide technical support for shale oil well production prediction and production analysis.

The dynagraph card plays a crucial role in evaluating oilfield pumping systems’ performance. Nevertheless, classifying dynagraph cards can be quite difficult because certain operating conditions may exhibit similar patterns. Conventional classification approaches mainly involve labor-intensive manual analysis of these cards, leading to subjectivity, prolonged processing times, and vulnerability to human prejudices. In response to this challenge, our study introduces a novel approach that leverages transfer learning and the Swin Transformer model for classifying dynagraph cards across various operating conditions in rod pumping systems. Initially, the Swin Transformer model undergoes pre-training using the ImageNet-22k dataset. Subsequently, we fine-tune the model’s weights using actual dynagraph card datasets, facilitating direct classification analysis with dynagraph cards as input variables. The adoption of transfer learning significantly reduces the training time while enhancing the accuracy of condition diagnosis. To assess the effectiveness of our proposed method, we conducted a comparative evaluation against conventional models like ResNet50, DenseNet121, LeNet, and ViT. The findings demonstrate that our approach outperforms other methods, achieving an accuracy of 96%, thereby improving classification accuracy by 3–4%. Therefore, our approach, based on transfer learning and the Swin Transformer model, provides a better solution for practical problems involving similar dynagraph cards. It meets the requirements of oil field operations, enhancing economic benefits and work efficiency.

Reinjecting produced methane offers cost-efficiency and environmental benefits for enhances oil recovery. High minimum miscibility pressure (MMP) in methane-oil systems poses a challenge. To overcome this, researchers are increasingly focusing on using surfactants to reduce MMP, thus enhancing the effectiveness of methane injections for oil recovery. This study investigated the impact of pressure and temperature on the equilibrium interfacial tension of the CH4+n-decane system using molecular dynamics simulations and the vanishing interfacial tension technique. The primary goal was to assess the potential of surfactants in lowering MMP. Among four tested surfactants, ME-6 exhibited the most promise by reducing MMP by 14.10% at 373 K. Key findings include that the addition of ME-6 enriching CH4 at the interface, enhancing its solubility in n-decane, improving n-decane diffusion capacity, CH4 weakens n-decane interactions and strengthens its own interaction with n-decane. As the difference in interactions of n-decane with ME-6's ends decreases, the system trends towards a mixed phase. This research sets the stage for broader applications of mixed-phase methane injection in reservoirs, with the potential for reduced gas flaring and environmental benefits.

To address the challenges of low accuracy and complex influencing factors in predicting horizontal well fracturing productivity during the development of unconventional oil and gas resources such as tight oil, this paper proposes a productivity prediction framework based on an improved feature selection method and an ensemble learning model. This study employs a fusion analysis using the entropy weight method to combine Pearson correlation analysis and improved gray relational analysis (IGRA) for feature selection. Thirteen machine learning models were tested with six distinct parameter combinations to construct a Stacking-based ensemble learning model, with base models including Random Forest (RF), Ridge Regression (RR), and Artificial Neural Network (ANN). Particle Swarm Optimization (PSO) was employed to optimize hyperparameters, followed by interpretability analysis using SHapley Additive exPlanations (SHAP). The results indicate that the model with fused weights demonstrated optimal performance. The Stacking model achieved significantly improved accuracy after PSO optimization, with the coefficient of determination increasing by 4.9%, outperforming all comparison models. Engineering guidance is provided: Under current geological conditions, sand ratio and displacement fluid volume require fine-tuning to prevent over-treatment. Fracturing design should implement differentiated strategies based on the target sand body thickness. This study not only delivers a high-precision production prediction tool but also offers decision support for efficient unconventional oil and gas field development through its exceptional interpretability.