Training deep learning models on synthetic data is a common practice in geophysics. However, knowledge transfer from synthetic to field applications is often a bottleneck. Here, we describe the workflow for the generation of a realistic synthetic dataset of elastic waveforms, sufficient for low-frequency extrapolation in marine streamer setup. Namely, we first extract the source signature, the noise imprint, and a 1D velocity model from real marine data. Then, we use those to generate pseudorandom initializations of elastic subsurface models and simulate elastic wavefield data. After that, we enrich the simulated data with realistic noise and use it to train a deep neural network. Finally, we demonstrate the results of low-frequency extrapolation on field streamer data, given that the model was trained exclusively on a synthetic dataset.
|Original language||English (US)|
|Title of host publication||82nd EAGE Annual Conference & Exhibition|
|Publisher||European Association of Geoscientists & Engineers|
|State||Published - 2021|
Bibliographical noteKAUST Repository Item: Exported on 2021-10-06
Acknowledgements: The research reported in this publication was supported by funding from King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia. We also thank Mahesh Kalita and Abdullah Alali from KAUST for their help.