Reservoir Quality Index Prediction Method Based on CNN and BiGRU
LI Jianping
ZHANG Zixuan
Abstract：This paper proposes a low-permeability oilfield reservoir quality index prediction method based on the combination of one-dimensional convolutional neural network(1DCNN)and bidirectional gated recurrent unit(BiGRU).The above part of the logging sequence data is used as input,and the convolution kernel is used to extract the characteristics of these data features,and the bidirectional GRU is used to update the eigenvalues in the forward and reverse order.The coefficients are multiplied by the corre-sponding features,and the values of the curve series corresponding to the next depth are predicted,and finally the reservoir quality index(RQI)is obtained.And this model is compared with other machine learning network models.The results show that the 1DCNN-BiGRU model designed in this paper is better than the BP neural network and the CNN convolutional neural network in terms of prediction accuracy of the reservoir quality index prediction method for low permeability oilfield reservoirs.
Keywords：low permeability oilfieldsCNNBiGRUreservoir quality indexreservoir characteristics
Publication Date：2025-04-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 989-994,1001 )