Reconstructing seismic data by incorporating deep external and internal learning

Seismic data interpolation is an essential procedure in seismic data processing. However, conventional interpolation methods may generate inaccurate results due to the simplicity of assumptions, such as linear events or sparsity. On the contrary, deep learning trains a deep neural network with a large dataset without relying on predefined assumptions. However, the lack of physical prior in the traditional pure data-driven deep learning frameworks may cause low generalization for different sampling patterns. Inspired by the project onto convex sets (POCS) framework, a new neural network is proposed for seismic interpolation, named POCS-Net. The forward Fourier transform, inverse Fourier transform, and the threshold parameter in POCS are replaced by neural networks that are independent in different iterations. The threshold is trainable in POCS-Net rather than manually set. A nonnegative constraint is imposed on the threshold to make it consistent with traditional POCS. POCS-Net is essentially an end-to-end neural network with priors of sampling pattern and a pre-defined iterative framework. Numerical results on 3D synthetic and field seismic datasets demonstrate the superiority of reconstruction accuracy of the proposed method compared to the traditional and natural image-learned POCS methods.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Reconstructing seismic data by incorporating deep external and internal learning

Cited by 2 publications

References 21 publications

Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach

Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach

A projection-onto-convex-sets network for 3D seismic data interpolation

Contact Info

Product

Resources

About