The production of a single gas well is influenced by many geological and completion factors. The aim of this paper is to build a production prediction model based on machine learning technique and identify the most important factor for production. Firstly, around 159 horizontal wells were collected, targeting the Duvernay Formation with detailed geological and completion records. Secondly, the key factors were selected using grey relation analysis and Pearson correlation. Then, three statistical models were built through multiple linear regression (MLR), support vector regression (SVR), gaussian process regression (GPR). The model inputs include fluid volume, proppant amount, cluster counts, stage counts, total horizontal lateral length, gas saturation, total organic carbon content, condensate-gas ratio. The model performance was assessed by root mean squared errors (RMSE) and R-squared value. Finally, sensitivity analysis was applied based on best performance model. The analysis shows following conclusions: (1) GPR model shows the best performance with the highest R-squared value and the lowest RMSE. In the testing set, the model shows a R-squared of 0.8 with a RMSE of 280.54 × 104 m3 in the prediction of cumulative gas production within 1st 6 producing months and gives a R-squared of 0.83 with a RMSE of 1884.3 t in the prediction of cumulative oil production within 1st 6 producing months (2) Sensitivity analysis based on GPR model indicates that condensate-gas ratio, fluid volume, and total organic carbon content are the most important features to cumulative oil production within 1st 6 producing months. Fluid volume, Stages, and total organic carbon content are the most significant factors to cumulative gas production within 1st 6 producing months. The analysis progress and results developed in this study will assist companies to build prediction models and figure out which factors control well performance.
In this paper, taking Block G in Canada as an example, combined with the data of the working area, the Pearson–MIC comprehensive evaluation method was adopted to optimize the key parameters of productivity. Based on the analytic hierarchy process, the weight of each parameter was calculated, the grade of evaluation index of the “sweet spot” was divided, the standard of the sweet spot was established, and the distribution of the superimposed sweet spot was finally depicted. The results show that lateral length, number of stages, volume of fluid, and amount of proppant are the key engineering parameters of horizontal well, and lateral length is an independent key engineering parameter. The cumulative gas production in the first two years was normalized on the lateral length to eliminate the engineering influence, and the total organic carbon (TOC) was finally determined as the key geological parameter, whereas porosity and water saturation were the secondary key parameters. The area of Type I sweet spots accounts for 24.2% in the Series Upper and 23.1% in the Series Lower. This study proposed a new sweet spot prediction idea based on the influence of geological factors on productivity, and its results also laid a foundation for the subsequent placement of horizontal wells in Block G.
The dynamic productivity prediction of shale condensate gas reservoirs is of great significance to the optimization of stimulation measures. Therefore, in this study, a dynamic productivity prediction method for shale condensate gas reservoirs based on a convolution equation is proposed. The method has been used to predict the dynamic production of 10 multi-stage fractured horizontal wells in the Duvernay shale condensate gas reservoir. The results show that flow-rate deconvolution algorithms can greatly improve the fitting effect of the Blasingame production decline curve when applied to the analysis of unstable production of shale gas condensate reservoirs. Compared with the production decline analysis method in commercial software HIS Harmony RTA, the productivity prediction method based on a convolution equation of shale condensate gas reservoirs has better fitting affect and higher accuracy of recoverable reserves prediction. Compared with the actual production, the error of production predicted by the convolution equation is generally within 10%. This means it is a fast and accurate method. This study enriches the productivity prediction methods of shale condensate gas reservoirs and has important practical significance for the productivity prediction and stimulation optimization of shale condensate gas reservoirs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.