Productivity prediction has always been an important part of reservoir development, and tight reservoirs need accurate and efficient productivity prediction models. Due to the complexity of the tight oil reservoir, the data obtained by the detection instrument need to extract data features at a deeper level. Using the Pearson correlation coefficient and partial correlation coefficient to analyze the main control of productivity factors, eight characteristic parameters of volume coefficient, water saturation, density, effective thickness, skin factor, shale content, porosity, and effective permeability were obtained, and the specific oil production index was used as the target parameter. Two sample structures of pure static parameters and dynamic and static parameters (shale content, effective permeability, porosity, water saturation, and density as dynamic parameters, volume coefficient, skin factor, and effective thickness as static parameters) were created, and corresponding model structures (BP (Backpropagation), neural network model, and LSTM-BP (Long Short-Term Memory Backpropagation) neural network model) were designed to compare the prediction effects of models under different sample structures. The mean absolute error, root mean square error, mean relative percentage error, and coefficient of determination were used to evaluate the model results. The LSTM-BP neural network was used to predict the production capacity of the test set. The results showed that the average absolute error was 0.07, the root mean square error was 0.10, the average absolute percentage error was 21%, and the coefficient of determination was 0.97. Using wells in the WZ area for testing, the LSTM-BP model’s predictions are evenly distributed on both sides of the 45° line, separating the predicted values from actual values, with errors from the line being relatively small. In contrast, the BP model and analytical method are unable to achieve such an even distribution around the line. Experiments show that the LSTM-BP neural network model can effectively extract dynamic parameter features and has a stronger generalization ability.

Single-well productivity is a crucial metric for assessing the effectiveness of petroleum reservoir development. The accurate prediction of productivity is essential for achieving the efficient and economical development of oil–gas reservoirs. Traditional productivity prediction methods (empirical formulae and numerical simulation) are limited to specific reservoir types. There are few influencing factors, and a large number of ideal assumptions are made for the assumed conditions when predicting productivity. The application scenario is ideal. However, in tight oil reservoirs, numerous factors affect productivity, and their interactions exhibit significant complexity. Continuing to use traditional reservoir productivity prediction methods may result in significant calculation errors and lead to economic losses in oilfield development. To enhance the accuracy of tight reservoir productivity predictions and achieve economical and efficient development, this paper investigates the tight reservoir in the WZ block of the Beibuwan area, considering the impact of geological and engineering factors on productivity; the random forest tree and Spearman correlation coefficient are used to analyze the main influencing factors of productivity. The back propagation neural network optimized by particle swarm optimization was employed to develop a productivity prediction model (PSO-BP model) for offshore deep and ultra-deep tight reservoirs. The actual test well data of the oilfield are substituted into this model. The analysis results of the example application yielded an RMSE of 0.032, an MAE of 1.209, and an R² value of 0.919. Compared with traditional productivity prediction methods, this study concludes that the model is both reasonable and practical. The calculation speed is faster and the calculation result is more accurate, which can greatly reduce productivity errors. The model constructed in this paper is well suited for predicting the productivity of tight reservoirs within the WZ block. It offers substantial guidance for predicting the productivity of similar reservoirs and supports the economical and efficient development of petroleum reservoirs.

Several methods are currently used to test offshore tight reservoirs. However, the effectiveness of these applications varies among wells, and some exhibit unclear reservoir classifications. These issues lead to difficulties in decision-making during tests and result in higher testing costs. Therefore, to address this issue, this study used reservoirs in the Liushagang Formation of the Beibu Basin as the research object and employed core data to apply the multi-stage FZI method. This method computes the FZI and its cumulative probability, classifying the target reservoir into seven distinct types. According to the Winland R₃₅ method, the target reservoir was classified into five distinct types. Seven characteristic parameters were selected based on the mercury injection experimental data. The K-means clustering method was then used to classify the target reservoirs into two types. The conclusions were that, in this formation, there is predominantly low to extra-low porosity and extra-low to ultra-low permeability. According to relationship models, logged porosity can be used to calculate effective permeability. Combining the multi-stage FZI method with the K-means clustering method for reservoir classification is recommended. This integrated approach facilitates a more comprehensive analysis of the characteristics of offshore low-permeability tight reservoirs at both macro and micro scales after classification. This research provides key insights for enhancing offshore well production.

This study addresses the challenge of rapidly and accurately predicting the production of test wells in offshore tight oil reservoirs, specifically within the L Formation of the Beibu Basin. This challenge is particularly pronounced in situations where drill stem tests are limited and evaluating each untested well layer is difficult. To achieve this objective, we analyzed fifteen typical test wells in the L Formation, taking into account both geological and engineering factors. Initially, Pearson correlation analysis, partial correlation analysis, and grey relational analysis were used to identify the main production factors. Based on these analyses, two types of production prediction models were developed: one employing the comprehensive production index method and the other utilizing the production coefficient method. The research identified effective permeability, porosity, oil saturation, and shale content as the main production factors for the test wells in the study area. The model verification results showed that the comprehensive production index model performs effectively for the L Formation, with an average prediction error of 20.40% compared to the actual production values. This research is significant for optimizing and stabilizing production in tight oil reservoirs.