MathWorks - Mobile View
  • Sign In to Your MathWorks AccountSe connecter
  • Access your MathWorks Account
    • Mon compte
    • Mon profil
    • Mes licences
    • Se déconnecter
  • Produits
  • Solutions
  • Le monde académique
  • Support
  • Communauté
  • Événements
  • Obtenir MATLAB
MathWorks
  • Produits
  • Solutions
  • Le monde académique
  • Support
  • Communauté
  • Événements
  • Obtenir MATLAB
  • Sign In to Your MathWorks AccountSe connecter
  • Access your MathWorks Account
    • Mon compte
    • Mon profil
    • Mes licences
    • Se déconnecter

Vidéos et webinars

  • MathWorks
  • Vidéos
  • Vidéos
  • Recherche
  • Vidéos
  • Recherche
  • Contacter un commercial
  • Version d'essai
  Register to watch video
  • Description
  • Related Resources

MATLAB Oil and Gas Conference 2019: Seismic Analysis with Wavelets and Deep Learning

From the series: MATLAB Oil and Gas Conference 2019

Akhilesh Mishra, MathWorks

Seismic reflection analysis is the most common method to obtain subsurface information for reservoir characterization. However, seismic reflection is often distorted by complex salt bodies and other geological structures and its vertical resolution is often of the order of dozens of meters. In addition, analyzing large amounts of seismic data is a computationally challenging and time-consuming task. To circumvent these challenges, in this work, we present an approach using wavelets and deep learning to accelerate seismic analysis tasks.

While considerable attention has already been focused on the use of wavelet transforms for seismic data compression, we combine it with deep learning to address the problem of distortion of seismic data. The field studies were done on seismic data from Antarctica, and we could clearly identify the interfaces between ice sheet and bed rock. Our recent results have demonstrated that wavelets combined with deep learning can distinguish among different facies, helping the interpreter to process new seismic images. The great advantage of this method over using just deep learning is the reduction in the amount of labeled data needed for training. We also present very quick-to-prototype algorithms in MATLAB® that can classify parts of the image with high accuracy. The final part of this work includes deploying this deep learning network on a GPU to perform the facies recognition real time on a stand-alone embedded hardware.

Related Products

  • Wavelet Toolbox
  • Deep Learning Toolbox
  • Signal Processing Toolbox

Learn More

MATLAB for Deep Learning
Related Information
MATLAB for the Oil and Gas Industry

Feedback

Featured Product

Wavelet Toolbox

  • Request Trial
  • Get Pricing

Up Next:

Gustavo Sanchez from Pandata Tech addresses some common misconceptions about MATLAB vs. open source.
24:14
MATLAB and Open Source
View full series (7 Videos)

Related Videos:

4:27
Peak Analysis
42:45
Signal Processing and Machine Learning Techniques for...
39:18
Signal Processing for Machine Learning
27:15
MATLAB Analysis of Prestack Seismic: Using MATLAB Beyond...
8:51
MATLAB Analysis of Prestack Seismic: Using MATLAB Beyond...

View more related videos

MathWorks - Domain Selector

Select a Web Site

Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .

Select web site

You can also select a web site from the following list:

How to Get Best Site Performance

Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.

Americas

  • América Latina (Español)
  • Canada (English)
  • United States (English)

Europe

  • Belgium (English)
  • Denmark (English)
  • Deutschland (Deutsch)
  • España (Español)
  • Finland (English)
  • France (Français)
  • Ireland (English)
  • Italia (Italiano)
  • Luxembourg (English)
  • Netherlands (English)
  • Norway (English)
  • Österreich (Deutsch)
  • Portugal (English)
  • Sweden (English)
  • Switzerland
    • Deutsch
    • English
    • Français
  • United Kingdom (English)

Asia Pacific

  • Australia (English)
  • India (English)
  • New Zealand (English)
  • 中国
    • 简体中文Chinese
    • English
  • 日本Japanese (日本語)
  • 한국Korean (한국어)

Contact your local office

  • Contacter un commercial
  • Version d'essai

Découvrir les produits

  • MATLAB
  • Simulink
  • Version étudiante
  • Support Hardware
  • File Exchange

Essayer ou Acheter

  • Téléchargements
  • Version d'essai
  • Contacter un commercial
  • Tarifs et licences
  • Comment acheter

Se Former

  • Documentation
  • Tutoriels
  • Exemples
  • Vidéos et webinars
  • Formation

Obtenir de l'aide

  • Aide à l'installation
  • Forum MATLAB
  • Services de consulting
  • Gestion Licences
  • Contacter le support technique

La société

  • Offres d'emploi
  • Actualités
  • Social Mission
  • Contacter un commercial
  • La société

MathWorks

Accelerating the pace of engineering and science

MathWorks est le leader mondial des logiciels de calcul mathématique pour les ingénieurs et les scientifiques.

Découvrir…

  • Select a Web Site United States
  • Brevets
  • Marques déposées
  • Charte de confidentialité
  • Lutte anti-piratage
  • État des applications

© 1994-2021 The MathWorks, Inc.

  • Facebook
  • Twitter
  • Instagram
  • YouTube
  • LinkedIn
  • RSS

Rejoignez la conversation

This website uses cookies to improve your user experience, personalize content and ads, and analyze website traffic.  By continuing to use this website, you consent to our use of cookies.  Please see our Privacy Policy to learn more about cookies and how to change your settings.