Improvement of Spectrum Suppression Based Deep Learning Interpolation Technique

Seismic data are often coarsely or inconsistently sampled along the acquisition geometry due to inherent limitations in survey equipment or insufficient survey budgets. Recently, machine learning techniques have been utilized to acquire compactly sampled seismic data. Among them, the self-supervised learning-based techniques that do not require labels are actively being used, and the interpolation technique based on the blind trace network (BTN) and spectrum suppression using suppression masks through line detection has shown high accuracy. However, the interpolation technique using BTN and the suppression masks through line detection suffers from instability caused by the reconstruction loss and inaccuracy of the suppression masks. To mitigate those problems, we propose suppression masks using a generalized frequency–wavenumber ( f – k ) trace interpolation (GFKI), patch-based learning, masked UNet, and the equalized learning rate. The suppression masks using GFKI are generated by correlating the zero-padded data with the data obtained by regularly removing traces from the zero-padded data in the f – k domain. In addition, we divide data into patches to enhance the accuracy of the suppression masks. Masked UNet is used to constrain the output to contain the input signals at the designated positions using the binary mask in the space–time domain. Furthermore, we normalize each layer in the network so that the learning speeds for each layer can be commensurate with each other. The synthetic and field data experiments show that the proposed interpolation technique effectively suppresses the aliasing of signals and enables the training process to stably converge.