STORSEISMIC: AN APPROACH TO PRE-TRAIN A NEURAL NETWORK TO STORE SEISMIC DATA FEATURES

M. R.C. Harsuko, T. A. Alkhalifah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Machine Learning (ML) has recently been helpful for many seismic processing and imaging tasks. However, these tasks are often handled separately with their own neural network model and training. We propose StorSeismic, a unified framework to store the features in seismic data and use them later for varying seismic processing tasks. Through the help of the self-attention mechanism embedded in the Bidirectional Encoder Representation from Transformers (BERT), a Transformer-based network architecture, we capture and store the local and global features of seismic data in the pre-training stage, then utilize them in various seismic processing tasks in the fine-tuning stage. Using this framework, we could achieve a more efficient and flexible training process than existing approaches. Two applications on denoising and velocity estimation demonstrate the flexibility and the potential of this proposed framework in adapting to various seismic processing tasks.

Original languageEnglish (US)
Title of host publication83rd EAGE Conference and Exhibition 2022
PublisherEuropean Association of Geoscientists and Engineers, EAGE
Pages1088-1092
Number of pages5
ISBN (Electronic)9781713859314
StatePublished - 2022
Event83rd EAGE Conference and Exhibition 2022 - Madrid, Virtual, Spain
Duration: Jun 6 2022Jun 9 2022

Publication series

Name83rd EAGE Conference and Exhibition 2022
Volume2

Conference

Conference83rd EAGE Conference and Exhibition 2022
Country/TerritorySpain
CityMadrid, Virtual
Period06/6/2206/9/22

ASJC Scopus subject areas

  • Geochemistry and Petrology
  • Geophysics

Fingerprint

Dive into the research topics of 'STORSEISMIC: AN APPROACH TO PRE-TRAIN A NEURAL NETWORK TO STORE SEISMIC DATA FEATURES'. Together they form a unique fingerprint.

Cite this