Gas-bearing prediction in tight sandstone reservoirs based on multinetwork integration

Tight sandstone reservoir gas is an important component of unconventional natural gas exploration and production in China. However, tight sandstone reservoirs have the characteristics of poor lateral continuity, strong vertical heterogeneity, complex lithology, and large changes in physical properties, which means traditional oil and gas evaluation sometimes suffers from low accuracy. Therefore, a method for predicting the gas content of tight sandstone reservoirs is developed. This method selects seismic attributes through Pearson coefficients, combines multiple attribute information, and inputs it into a deep neural network. This study constructed MultipleNet by combining a convolutional neural network, a bidirectional gated neural unit network, and a self-attention mechanism. This network takes advantage of the complementary advantages of the preceding network modules and can more effectively mine information on various seismic attributes and improve gas-bearing prediction accuracy. This method is applied to actual data from a tight sandstone gas exploration area in the Sichuan Basin. Experimental results indicate that the results of well-side predictions using this method are consistent with well data, providing a new approach and perspective for predicting gas bearing in tight sandstone reservoirs.