English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We propose a convolutional neural network (CNN) denoising based method forseismic data interpolation. It provides a simple and efficient way to breakthough the lack problem of geophysical training labels that are often requiredby deep learning methods. The new method consists of two steps: (1) Train a setof CNN denoisers from natural image clean-noisy pairs to learn denoising; (2)Integrate the trained CNN denoisers into project onto convex set (POCS)framework to perform seismic data interpolation. The method alleviates thedemanding of seismic big data with similar features as applications ofend-to-end deep learning on seismic data interpolation. Additionally, theproposed method is flexible for many cases of traces missing because missingcases are not involved in the training step, and thus it is of plug-and-playnature. These indicate the high generalizability of our approach and thereduction of the need of the problem-specific training. Primary results onsynthetic and field data show promising interpolation performances of thepresented CNN-POCS method in terms of signal-to-noise ratio, de-aliasing andweak-feature reconstruction, in comparison with traditional $f$-$x$ predictionfiltering and curvelet transform based POCS methods.

Can learning from natural image denoising be used for seismic data interpolation?