论文信息 - Generative Adversarial Networks for Model Order Reduction in Seismic Full-Waveform Inversion

Generative Adversarial Networks for Model Order Reduction in Seismic Full-Waveform Inversion

I train a Generative Adversarial Network to produce realistic seismic wave speed models. I integrate the generator network into seismic Full-Waveform Inversion to reduce the number of model parameters and restrict the inverted models to only those that are plausible. Applying the method to a 2D section of the SEAM model, I demonstrate that it can produce more plausible results than conventional Full-Waveform Inversion.

Alan Richardson | Alan Richardson

[1] Yoshua Bengio,et al. Generative Adversarial Nets , 2014, NIPS.

[2] Denes Vigh,et al. Deep learning prior models from seismic images for full-waveform inversion , 2017 .

[3] Felix J. Herrmann,et al. Total Variation Regularization Strategies in Full-Waveform Inversion , 2016, SIAM J. Imaging Sci..

[4] Soumith Chintala,et al. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[5] Michael Fehler,et al. SEAM Phase 1: Challenges of Subsalt Imaging in Tertiary Basins, with Emphasis on Deepwater Gulf of Mexico , 2011 .

[6] Lukas Mosser,et al. Rapid seismic domain transfer: Seismic velocity inversion and modeling using deep generative neural networks , 2018, 80th EAGE Conference and Exhibition 2018.

[7] Felix J. Herrmann,et al. Seismic Data Reconstruction with Generative Adversarial Networks , 2018, 80th EAGE Conference and Exhibition 2018.