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

Traditional seismic processing workflows (SPW) are expensive, requiring overa year of human and computational effort. Deep learning (DL) based data-drivenseismic workflows (DSPW) hold the potential to reduce these timelines to a fewminutes. Raw seismic data (terabytes) and required subsurface prediction(gigabytes) are enormous. This large-scale, spatially irregular time-seriesdata poses seismic data ingestion (SDI) as an unconventional yet fundamentalproblem in DSPW. Current DL research is limited to small-scale simplifiedsynthetic datasets as they treat seismic data like images and process them withconvolution networks. Real seismic data, however, is at least 5D. Applying 5Dconvolutions to this scale is computationally prohibitive. Moreover, rawseismic data is highly unstructured and hence inherently non-image like. Wepropose a fundamental shift to move away from convolutions and introduce SESDI:Set Embedding based SDI approach. SESDI first breaks down the mammoth task oflarge-scale prediction into an efficient compact auxiliary task. SESDIgracefully incorporates irregularities in data with its novel modelarchitecture. We believe SESDI is the first successful demonstration ofend-to-end learning on real seismic data. SESDI achieves SSIM of over 0.8 onvelocity inversion task on real proprietary data from the Gulf of Mexico andoutperforms the state-of-the-art U-Net model on synthetic datasets.

Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion