Open AccessImproving the resolution of migrated images by approximating the inverse Hessian using deep learning
Author(s) -
Harpreet Kaur,
Nam Pham,
Sergey Fomel
Publication year - 2020
Publication title -
geophysics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.178
H-Index - 172
eISSN - 1942-2156
pISSN - 0016-8033
DOI - 10.1190/geo2019-0315.1
Subject(s) - hessian matrix , computer science , artificial neural network , algorithm , inversion (geology) , inverse , amplitude , inverse problem , matching (statistics) , artificial intelligence , synthetic data , pattern recognition (psychology) , mathematics , statistics , geology , paleontology , mathematical analysis , physics , geometry , structural basin , quantum mechanics
We have estimated migrated images with meaningful amplitudes matching least-squares migrated images by approximating the inverse Hessian using generative adversarial networks (GANs) in a conditional setting. We use the CycleGAN framework and extend it to the conditional CycleGAN such that the mapping from the migrated image to the true reflectivity is subjected to a velocity attribute condition. This algorithm is applied after migration and is computationally efficient. It produces results comparable to iterative inversion but at a significantly reduced cost. In numerical experiments with synthetic and field data sets, the adopted method improves image resolution, attenuates noise, reduces migration artifacts, and enhances reflection amplitudes. We train the network with three different data sets and test on three other data sets, which are not a part of training. Tests on validation data sets verify the effectiveness of the approach. In addition, the field-data example also highlights the effect of the bandwidth of the training data and the quality of the velocity model on the quality of the deep neural network output.