Crossline Reconstruction of 3D Seismic Data Using 3D cWGAN: A Comparative Study on Sleipner Seismic Survey Data

In seismic data acquisition, loss can occur, particularly with the use of streamer systems in marine exploration. These often cause spatial aliasing problems by having close inline intervals and wide crossline to maximize exploration range. To improve resolution direction, various machine learning techniques have been employed for reconstruction. this study, we introduce a 3D cWGAN (conditional Wasserstein generative adversarial network) interpolating data. We evaluate model’s performance comparing it 2D U-Net. two interpolation strategies are reconstruct missing direction. The first strategy uses network, which trains model using applies trained direction via cWGAN. second employs volume directly demonstrate effectiveness proposed method Sleipner CO2 4D survey dataset. Our results show that is more efficient enhancing computation compared or