High-resolution seismic reservoir monitoring with multitask and transfer learning

Ahmed Mohamed Ahmed, Ilya Tsvankin, Yanhua Liu

High-resolution real-time monitoring of reservoir changes is essential during CO2 injection or hydrocarbon production. Here, we leverage convolutional neural networks (CNNs) that employ multitask (MTL) and transfer (TL) learning to accurately predict relevant reservoir parameters from time-lapse seismic data. CNNs are initially trained to estimate the P-wave velocity from 2D multicomponent seismic data and then are fine-tuned through TL to obtain the S-wave velocity, density, and saturation. This methodology is applied to a synthetic CO2 sequestration model based on California’s Kimberlina storage reservoir. When using MTL, CNNs are trained simultaneously on several related tasks by taking advantage of their commonalities. We show that after pretraining the model on a 2D line, it can be fine-tuned to predict the reservoir parameters from the data acquired in the crossline direction. Our work addresses the challenge of training-data scarcity, promotes efficient use of computational resources in reservoir monitoring, and helps increase the accuracy of real-time monitoring of the fluid movement inside the reservoir.