A geophysical prior knowledge guided semisupervised deep learning framework for AVA inversion
Lei Zhu · 2024
Supervised deep learning methods currently used for prestack parameter prediction are limited by the small sample issue. The lack of clear physical meanings for deep learning models also makes prediction results unreliable. To address these issues, we developed a geophysical prior knowledge guided semisupervised (GPKGS) deep learning framework for amplitude-versus-angle (AVA) inversion. Based on physical priori knowledge, the prestack seismic data are decoupled into prestack seismic attribute data of the reservoir parameters. Meanwhile, according to the prestack seismic attribute data, constructing the new forward models corresponding to each reservoir parameter. The intelligent inversion framework is built based on the constructed forward model. This reduces the dependence of the framework on training data. This GPKGS framework preserves the physical process of AVA inversion, making intelligent inversion results reliable. The framework contains three branch networks of reservoir parameters. Each branch network contains an inversion neural network (INN) and a forward neural network (FNN). The INN can invert the prestack seismic attribute data into reservoir parameters, which corresponding to inversion process. The FNN convert the obtained reservoir parameters into synthetic prestack seismic attribute data, which corresponding to forward process. To ensure a reliable training process, the difference between the prestack seismic attribute data and the synthetic data are used to train the framework supervised by well log data. In addition, to obtain more stable results, after training, the priori information data are also introduced to help the FNN update the reservoir parameters obtained by INN. Marmousi2 models is used to test the proposed framework. We find that the intelligent inversion results of the proposed network can have a good performance on the situation of less train data.