Posted by Khalid Almuteri

Figure 1. Comparison among (a) true ghost-free, (b) ghost-contaminated, and (c) ghost-free prediction shot gathers. (d–f) After applying 20 Hz high-cut filtering in (a–c), respectively.

Ghost reflections deteriorate the quality of seismic data in towed-streamer acquisition, and various acquisition and processing solutions have been proposed to remove them from seismic data. A common issue with the proposed solutions is their limited ability to remove source-side ghosts because of the sparse source sampling. Satisfactory receiver-side deghosting solutions are facilitated by complementary measurements (e.g., particle motion data) for wavefield separation and also can be achieved using pressure data acquired at a single recording level only. We develop a solution based on convolutional neural networks (CNNs) to remove source- and receiver-side ghosts in the shot domain. The solution does not require complementary measurements, that is, it can remove ghost reflections in conventional pressure data measured at a single recording level. Our method requires knowledge of the acquisition geometry to create training data that replicate the field acquisition geometry and require the ocean floor bathymetry to be known. A CNN learns to map ghost-contaminated gathers to corresponding ghost-free gathers through an iterative training process. We find that the CNN-based deghosting operator can remove ghost reflections from previously unseen data and demonstrate that the solution generalizes well when training is done on models unrelated to the actual field geology.

Figure 2. Comparison among the average amplitude spectra of the ghost-free data (black line), the ghost-contaminated data (red line), and the ghost-free prediction data (blue line). (a) Comparison between the full bandwidth data shown in Figure 1a–1c. (b) Comparison between the band-limited data shown in Figure 1d–1f.