Convolutional recurrent neural networks based waveform classification in seismic facies analysis

Abstract

Waveform classification is a useful method in seismic facies analysis and has been successfully applied to oil and gas reservoir prediction. In general, the problem can be solved by machine learning methods. However, the spatial continuity and similarity of adjacent traces are not considered adequately in these traditional methods. In the paper, this problem is addressed here by proposing a method based on the combined neural network and 2D structure of supervised sample. Specially, the use of combined neural network takes full advantages of some features of deep learning methods. Finally, this method is applied to a real case in Western China. The results show that the proposed method can improve the prediction accuracy of seismic facies in an efficient way. Presentation Date: Wednesday, September 18, 2019 Session Start Time: 1:50 PM Presentation Time: 2:40 PM Location: Poster Station 2 Presentation Type: Poster