Deep learning-based point-spread function deconvolution for migration image deblurring

High-resolution seismic imaging is crucial for deriving an ac-curate geologic section and ensuring successful petroleum explo-ration. However, traditional high-resolution imaging methods, such as least-squares reverse time migration (LSRTM) and migra-tion deconvolution, usually involve high computational costs for approximating the inverse Hessian matrix with limited improve-ments in resolution. To obtain high-resolution migration images and reduce computing costs, we present a deep learning-based point-spread function (PSF) deconvolution method. We decom-pose the large Hessian matrix into small dispersed PSFs and de-sign a convolutional neural network (CNN) to automatically predict the deconvolution operator of every single PSF. The de -convolution operator eliminates the PSF effect and balances the insufficient illumination of the acquisition geometry. To obtain an efficient CNN model for predicting deconvolution operators, we trained 2500 pairs of PSFs and their corresponding deconvo-lution operators collected from part of a model using the regular PSF deconvolution method. After training the network, we could predict all deconvolution operators in a few seconds for the fol-lowing processing of migration images. The results on synthetic and field-data applications indicate that our method could provide a deblurred migration image comparable to that of the LSRTM approaches with significantly reduced computational and memory costs.

Automated summary

This study proposes a deep learning-based point-spread function deconvolution method for high-resolution seismic imaging. By training a convolutional neural network to predict deconvolution operators, computational and memory costs can be significantly reduced while improving the quality of the images.