REVEAL STRATIGRAPHY
REVEAL STRATIGRAPHY
Using the Paradise AI workbench, geoscientists can generate and analyze seismic data at the sample level, well beyond a wavelet. This powerful capability, along with the application of machine learning to Multi-Attribute Classification, produces profound, sometimes surprising results, particularly the ability to detect features below conventional seismic tuning thickness. Attribute Selection is done through the use of Principal Component Analysis (PCA), and Multi-Attribute Classification is based on the highly robust Self-Organizing Map (SOM) technique, which is applicable with or without well control. This means these tools in the workbench are appropriate for both exploration and production.
Using the Paradise AI workbench, geoscientists can generate and analyze seismic data at the sample level, well beyond a wavelet. This powerful capability, along with the application of machine learning to Multi-Attribute Classification, produces profound, sometimes surprising results, particularly the ability to detect features below conventional seismic tuning thickness. Attribute Selection is done through the use of Principal Component Analysis (PCA), and Multi-Attribute Classification is based on the highly robust Self-Organizing Map (SOM) technique, which is applicable with or without well control. This means these tools in the workbench are appropriate for both exploration and production.
Key Features:

Enable interpreters to produce higher resolution interpretations of reservoirs and their stratigraphy
Improve confidence in interpreting DHI characteristics and more clearly define reservoir edges and thin bed components
Refine interpretations with a recipe of attributes that target specific investigations, such as stratigraphy, lithology, faulting, fracturing, fluids, pressure, etc.
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

Applied together (Attribute Generation + Attribute Selection + Multi-Attribute Classification), the guided ThoughtFlow® in Paradise has proven to define potential fluid effects on seismic data. The method has also demonstrated the ability to detect thin beds that are below classic seismic tuning thickness. Overall, deeper geological insights are gained into the zone of interest by improving the resolution of stratigraphic facies and their distributions.
- Identify and calibrate detailed stratigraphy
- Improve the interpretation of stratigraphic facies and their distributions
- Distinguish thin beds below conventional seismic tuning
- Interpret Direct Hydrocarbon Indicators
- Distinguish geologic features and their geometries
- Reveal fracture trends in shale plays
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.