An efficient data-driven global sensitivity analysis method of shale gas production through convolutional neural network

• DOI: 10.1016/j.petsci.2024.02.010
• Publication Date: 2024-02-22T05:36:38Z
• Authors: Liang Xue; Shuai Xu; Jie Nie; Ji Qin; Jiang-Xia Han; Yue-Tian Liu; Qin-Zhuo Liao
• Keywords: Sobol sequence; Shale Gas

The shale gas development process is complex in terms of its flow mechanisms and the accuracy production forecasting influenced by geological parameters engineering parameters. Therefore, to quantitatively evaluate relative importance model on performance, sensitivity analysis required. are ranked according coefficients for subsequent optimization scheme design. A data-driven global (GSA) method using convolutional neural networks (CNN) proposed identify influencing production. CNN trained a large dataset, validated against numerical simulations, utilized as surrogate efficient analysis. Our approach integrates with Sobol' method, presenting three key scenarios analysis: stage whole, fixed time intervals, declining rate. findings underscore predominant influence reservoir thickness well length Furthermore, temporal reveals dynamic shifts parameter across distinct stages.