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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semblance velocity analysis is a crucial step in seismic data processing. Toavoid the huge time-cost when performed manually, some deep learning methodsare proposed for automatic semblance velocity picking. However, the applicationof existing deep learning methods is still restricted by the shortage of labelsin practice. In this letter, we propose an attention neural network combinedwith a point-to-point regression velocity picking strategy to mitigate thisproblem. In our method, semblance patch and velocity value are served asnetwork input and output, respectively. In this way, global and local featureshidden in semblance patch can be effectively extracted by attention neuralnetwork. A down-sampling strategy based on horizontal layer extraction is alsodesigned to improve the picking efficiency in prediction process. Tests onsynthetic and field datasets demonstrate that the proposed method can producereasonable results and maintain global velocity trend consistent with labels.Besides, robustness against random noise is also tested on the field data.

Horizontal Layer Constrained Attention Neural Network for Semblance Velocity Picking