SEG 2019 – San Antonio

SEG 2019 – San Antonio

Geophysical Insights is featuring two new off-the-shelf, deep learning applications in the Paradise® AI workbench

Seismic Facies Classification and Fault Detection

STOP BY BOOTH #1038 FOR A DEMONSTRATION

SEG 2019, 15-20 September
Booth #1038

Solving interpretation problems with deep learning and machine learning technologies

Visit booth #1038 to hear industry thought leaders present applications of machine learning and deep learning technologies to seismic interpretation in different geologic settings.  Learn how technologies like GPU processing will change and enable geoscience workflows.  Here are a few of the topics:

  • Seismic facies classification using deep learning
  • Net reservoir discrimination through multi-attribute analysis
  • Thin bed detection with unsupervised machine learning
  • Case studies of machine learning in geologic settings
  • GPU processing for attribute generation

 

 

Geophysical Insights will be hosting daily lunch & learns at booth 1038 with featured talks by Fabian Rada, Dr. Tom Smith, and Dustin Dewett. Register for the lunch & Learns with the form on this page.

Gain Access to 2019 SEG Booth Presentations or Register for a Lunch & Learn


Speakers & Presentations

Dustin Dewett

Product Manager, Geophysical Insights
Seismic Facies Classification and Fault Detection using Deep Learning

Mike Dunn

SVP of Business Development, Geophysical Insights
Generating Attributes on GPUs

Reynaldo Gomez

Energy Account Manager, NVIDIA
Generating Attributes on GPUs

Dr. Bob Hardage

Geoscience Adviser, Geophysical Insights
Machine Learning Geobodies in the Wolfberry Play of the Permian Basin

Exposing Karst Topography in the Deep Ellenberger of the Permian Basin through Machine Learning

Dr. Carrie Laudon

Senior Geoscientist, Geophysical Insights
Machine Learning Improves Stratigraphic Resolution in the Niobrara

Dr. Ivan Marroquin

Senior Research Geophysicist, Geophysical Insights
Studies in Automated Optimization for Multi-Attribute Classification

Fabian Rada

Senior Adviser to PEMEX, Petroleum Oil & Gas Services
Net Reservoir Discrimination through Multi-Attribute Analysis at Single Sample Scale

Rocky Roden

Senior Geophysicist, Geophysical Insights
Comparing Machine Learning Methods and the Black Box Perception

Machine Learning on the Geoscience Technology Adoption Cycle

Deborah Sacrey

Senior Geoscientist, Geophysical Insights
A Journey through Paradise – Case Histories in Different Depositional Environments

Dr. Tom Smith

President & CEO, Geophysical Insights
Thin Bed Detection with Unsupervised Machine Learning

Mathematical Foundation for Machine Learning of Multi-Attribute Seismic Surveys

For a printable version of the schedule, click here

Presentation Schedule

Time Monday, 16 Sep Tuesday, 17 Sep Wednesday, 18 Sep
9:30-10:00 Exhibition opens at 10 AM Deborah Sacrey: A Journey through Paradise – Case Histories in Different Depositional Environments Deborah Sacrey: A Journey through Paradise – Case Histories in Different Depositional Environments
10:30-11:00 Bob Hardage: Machine Learning Geobodies in the Wolfberry Play of the Permian Basin

Rocky Roden: Comparing Machine Learning Methods and the Black Box Connotation

Carrie Laudon: Machine Learning Improves Stratigraphic Resolution in the Niobrara
12:00-1:00 Fabian Rada: Net Reservoir Discrimination through Multi-Attribute  Analysis at Single Sample Scale Tom Smith: Thin Bed Detection with Unsupervised Machine Learning Dustin Dewett: Seismic Facies Classification and Fault Detection using Deep Learning
1:30-2:30 Mike Dunn and Reynaldo Gomez: Generating Attributes on GPUs Carrie Laudon: Machine Learning Improves Stratigraphic Resolution in the Niobrara Rocky Roden: Machine Learning on the Geoscience Technology Adoption Cycle
3:00-4:00 Tom Smith:  Mathematical Foundation for Machine Learning of Multi-Attribute Seismic Surveys Dustin Dewett: Seismic Facies Classification and Fault Detection using Deep Learning Bob Hardage: Exposing Karst Topography in the Deep Ellenberger of the Permian Basin through Machine Learning
4:30-5:30 Dustin Dewett: Seismic Facies Classification and Fault Detection using Deep Learning Ivan Marroquin: Studies in Automated Optimization for Multi-Attribute Classification Exhibition closes at 4:30 PM

2019 Oil & Gas Machine Learning Symposium

2019 Oil & Gas Machine Learning Symposium

30 October 2019

Call for abstracts open now!

We are delighted to announce that Geophysical Insights will be the hosting sponsor for the second annual Oil & Gas Machine Learning Symposium, which is now open for abstracts. 

The 2018 Oil & Gas Machine Learning Symposium was a huge success as it hosted thought leaders from E&P companies, consulting firms, and large technology companies. This year’s Symposium will be even larger and more impactful. With a focus on geoscience, reservoir characterization, and technology, the Symposium will highlight developments in Machine Learning, Data Analytics, Cloud Computing, and the Industrial Internet of Things (IIoT). Together, technologies are enabling the Digital Transformation of the energy industry, starting upstream where hydrocarbons are found and monetized.

Join industry innovators on 30 October 2019 in Houston, Texas to share ideas, best practices, and key learnings in the development and application of machine learning technologies.

For more information on the 2019 Oil & Gas Machine Learning Symposium, Click Here.

 

URTeC 2019 – Denver

URTeC 2019 – Denver

22-24 July 2019

Machine Learning Applied to 3D Seismic Data from the Denver-Julesburg Basin Improves Stratigraphic Resolution in the Niobrara

Join us at URTeC 2019 hosted by SPE, SEG, and AAPG from 22-24 July 2019 where Carrie Laudon will be presenting “Machine Learning Applied to 3D Seismic Data from the Denver-Julesburg Basin Improves Stratigraphic Resolution in the Niobrara” with Paradise software.

For more information, please click here.

Webinar: Leveraging Deep Learning in Extracting Features of Interest from Seismic Data

Webinar: Leveraging Deep Learning in Extracting Features of Interest from Seismic Data

20 March 2019

We are delighted to kick off our quarterly machine learning webinar series this year with a presentation on applications of Convolutional Neural Networks (CNN) to seismic interpretation by Dr. Tao Zhao, Sr. Research Geophysicists with Geophysical Insights in Houston, Texas. Enabled by the development of GPU computing CNN, a form of deep learning, is proving to be an effective tool for many pattern recognition problems. Dr. Zhao will focus on three important applications of CNN that can have an immediate impact on interpretation workflows:

  • Seismic facies classification
  • Channel extraction
  • Fault detection

The webinar is free and runs an hour, including time for questions and answers at the end of the presentation.

Register today to attend the free webinar on Applications of Convolutional Neural Networks to Seismic Interpretation by Dr. Tao Zhao via the link below. You will receive a confirmation of your registration and details about how to log into the event upon registration. See below for the time of the webinar in your region.

Tao Zhao

Research Geophysicist | Geophysical Insights

TAO ZHAO joined Geophysical Insights in 2017. As a Research Geophysicist, Dr. Zhao develops and applies shallow and deep machine learning techniques on seismic and well log data, and advances multiattribute seismic interpretation workflows. He received a B.S. in Exploration Geophysics from the China University of Petroleum in 2011, an M.S. in Geophysics from the University of Tulsa in 2013, and a Ph.D. in geophysics from the University of Oklahoma in 2017. During his Ph.D. work at the University of Oklahoma, Dr. Zhao was an active member of the Attribute-Assisted Seismic Processing and Interpretation (AASPI) Consortium developing pattern recognition and seismic attribute algorithms.

Abstract:

Mapping and extracting features of interest is one of the most important objectives in seismic data interpretation. Due to the complexity of seismic data, geologic features identified by interpreters on seismic data using visualization techniques are often challenging to extract. With the rapid development in GPU computing power and the success obtained in computer vision, deep learning techniques, represented by convolutional neural networks (CNN), start to entice seismic interpreters in various applications. The main advantages of CNN over other supervised machine learning methods are its spatial awareness and automatic attribute extraction. The high flexibility in CNN architecture enables researchers to design different CNN models to identify different features of interest.

In this webinar, using several seismic surveys acquired from different regions, I will discuss three CNN applications in seismic interpretation: seismic facies classification, fault detection, and channel extraction. Seismic facies classification aims at classifying seismic data into several user-defined, distinct facies of interest. Conventional machine learning methods often produce a highly fragmented facies classification result, which requires a considerable amount of post-editing before it can be used as geobodies. In the first application, I will demonstrate that a properly built CNN model can generate seismic facies with higher purity and continuity. In the second application, compared with traditional seismic attributes, I deploy a CNN model built for fault detection which provides smooth fault images and robust noise degradation. The third application demonstrates the effectiveness of extracting large scale channels using CNN. These examples demonstrate that CNN models are capable of capturing the complex reflection patterns in seismic data, providing clean images of geologic features of interest, while also carrying a low computational cost.