DETECT FAULTS AUTOMATICALLY

DETECT FAULTS AUTOMATICALLY

Interpreters spend a tremendous amount of time identifying faults in seismic data. While this is a key process in seismic interpretation, most faults are straightforward, easy to see, and easy to understand. Fault detection is time-consuming, and it does not amplify the valuable skills and experiences an interpreter possesses. This repetitive task is ideally suited for the automated workflow available in Paradise 3.3.

Interpreters spend a tremendous amount of time identifying faults in seismic data. While this is a key process in seismic interpretation, most faults are straightforward, easy to see, and easy to understand. Fault detection is time-consuming, and it does not amplify the valuable skills and experiences an interpreter possesses. This repetitive task is ideally suited for the automated workflow available in Paradise 3.3.

Key Features:

Automatic Fault Detection

Fault Detection

Detect fault automatically and provide a volumetric prediction of faults

Pre-trained Models

Equip with general pre-trained CNN models (conservative and aggressive)

Deep Leaning Technology

Develop structural and stratigraphic seismic interpretation based on convolutional neural network (CNN) technology.

We have maintained for years that more can be gained from seismic data when it is analyzed using machine learning technology at a single sample resolution, and there is now an abundance of evidence to support this observation. We will continue to introduce off-the-shelf, fit-for-purpose applications to Paradise that have a strong return-on-investment for our customers.”

– Tom Smith, President & CEO of Geophysical Insights

Paradise seismic interpretation software monitor

Equipped with general pre-trained deep learning engines (conservative and aggressive), the new Deep Learning (DL) Fault Detection application in Paradise enables the application to a wide range of seismic data without the need of user-provided fault examples for training. This tool dramatically reduces the time to identify faults in a volume, which allows interpreters to spend more time on the implications of seismic data.

  • Improve fault continuity and resolution
  • Increase accuracy in fault detection
  • Reduce sensitivity to artifacts and noise
  • Produce fewer false positives
  • Generate a more accurate and complete understanding of the subsurface

KEY TECHNOLOGIES IN PARADISE AI WORKBENCH:

Seismic Facies Classification

Deep learning Seismic Facies Classification enables the identification of structural and stratigraphic facies patterns using Convolutional Neural Network (CNN) as an image recognition process.

Automatic Fault Detection

Equipped with general pre-trained deep learning engines (conservative and aggressive), Fault Detection in Paradise can be applied to a wide range of seismic data without the need of user-provided fault examples for training.

Multi-Attribute Classification

Applies machine learning to reveal thin beds below conventional tuning thickness.

Attribute Generation

The Paradise AI workbench has a world-class library of instantaneous, geometric, and spectral decomposition attributes. Over 100 attribute can be generated.

Geobody Detection

Uses machine learning to identify potential reservoirs and estimate reserves.

Attribute Selection

Principal Component Analysis (PCA), a guided ThoughtFlow® process, is to identify attributes that are contributing the most energy to a region.

  • Registration confirmation will be emailed to you.

  • We're committed to your privacy. Geophysical Insights uses the information you provide to us to contact you about our relevant content, events, and products. You may unsubscribe from these communications at any time. For more information, check out our Privacy Policy

    Scroll to Top