Seismic data interpolation with a recurrent inference mechanism

Abstract Seismic data interpolation is a significant procedure in seismic data processing as the highly complete data are extremely useful for the subsequent imaging and interpretation workflows. Recently, numerous deep learning-based techniques have been utilized to help improve the reconstruction quality. Supervised learning approaches can predict the results in a second, but they depend heavily on the training data, which therefore limits the generalized applications. By contrast, unsupervised learning methods are applicable to any data, but they need much more computational time and prior knowledge to be implemented. Especially, the recovery of aliased and consecutively missing data is incredibly challenging. To solve this problem, we propose a novel framework for seismic interpolation using a recurrent inference mechanism (SIRIM). Integrating the advantages of supervised and unsupervised learning paradigms, we build a specific convolutional recurrent inference network such that it can learn the dynamic priors when plugged in the physics-informed iterative algorithm, as well as directly reconstruct various types of incomplete data. We validate SIRIM in comparison with some traditional and learning-based methods. The performance on synthetic and field data illustrates the effectiveness and robustness of our proposed approach, which outperforms baseline methods in terms of aliased and consecutively missing data.