A Framework for Predicting the Gas-Bearing Distribution of Unconventional Reservoirs by Deep Learning

Abstract

Multicomponent seismic data can be used to predict unconventional reservoirs; however, this is a challenging task. Although machine learning (ML), particularly deep learning, can be used in this regard, its accuracy in reservoir prediction depends largely on the amount of data available for training and the complexity of the architecture. This study attempted to address this problem using transfer learning (TL) and a compact convolutional neural network with a self-attention mechanism (SACNN). We developed a framework for unconventional reservoir prediction by expanding the data samples and optimizing model performance. First, the synthetic data for both oil and gas reservoirs were used as the source data; their effectiveness was tested using the SACNN model. Subsequently, a real dataset was obtained by optimizing the real multicomponent seismic attributes. The TL dataset was constructed by transferring synthetic gas reservoir data to real dataset. Finally, the constructed SACNN model was used to predict the gas-bearing distribution in tight sandstone gas reservoirs. The results showed the superiority of the proposed model over conventional ML models, with lower error in the unconventional reservoir distribution prediction. Moreover, the proposed model exhibited superior prediction performance (R² = 0.9731) on the testing dataset compared to models trained solely on synthetic (R² = 0.9389) and real (R² = 0.9627) data. Moreover, uncertainty analysis showed that the proposed model is robust and efficient. The proposed framework provides a basis for constructing data-driven models for energy conversion and utilization.