Your AI tools await
Your AI Tools For Seismic Interpretation Await
Paradise® 3.4 equips geoscientists with more tools on the expanding AI workbench, making it the destination for interpreters who want reliable results fast. Check out the new features for viewing well logs alongside machine learning results, performing seismic data conditioning and analysis, and generating geometric attributes on GPU’s for faster performance.
Paradise® 3.4 equips geoscientists with more tools on the expanding AI workbench, making it the destination for interpreters who want reliable results fast. Check out the new features for viewing well logs alongside machine learning results, performing seismic data conditioning and analysis, and generating geometric attributes on GPU’s for faster performance.
Well Log Visualization
The new Well Log Visualization capability in Paradise 3.4 enables a corroboration among machine learning classification results, seismic attributes, and traditional well logs. Seismic data is presented at borehole and lithofacies resolution in feet/meters. Use the new Well Log Visualization capability to:
- Compare machine learning classification results and other seismic attributes to traditional well logs
- View well logs, formation tops, and extracted log curves together within a cross-section
- Customize the Well Log view by adding tracks and changing the properties of data
Well Log Visualization is a powerful tool for visually relating machine learning results to reservoir properties computed from conventional well logs. Access a technical paper via the button below on correlating machine learning classification results to the presence of a reservoir.
PSLi - Available shortly in a patch
PSLi is a dynamic, interactive application that comes with the pre-built scripts ready to apply. The capabilities include Conditioning, Analysis, Display, Import, and Export of data files. Here are some of the off-the-shelf features available in PSLi:
- Conditioning: Phase rotation, resample, filter, plus amplitude normalize, clip, and scale
- Analysis: Frequency spectrum, and frequency extracted wavelet
- Statistics: Average, mean, standard dev., maximum amplitude, and dead trace count
PSLi is also an environment for those developing applications in PSL, then serving those applications to other interpreters. Researchers and Data Scientists can write scripts in PSL, the powerful Paradise Scripting Language, then deploy those scripts as applications for general use through PSLi.
More Geometric (AASPI) Attributes on GPU
Paradise 3.4 offers faster generation of more geometric attributes using Graphics Processing Unit (GPU) computing. Now enjoy a dramatic reduction in generation time and more time for interpretation when using these powerful seismic attributes:
- Dip3D
- LUM Dip Filter
- GLCM
Paradise continues to be the go-to source for the world-class attributes from the Attribute-Assisted Seismic Processing & Interpretation (AASPI) consortium at the University of Oklahoma. Paradise is the only commercial software available that offers a comprehensive library of AASPI attributes, including geometric attributes and spectral decomposition, with an easy to use interface and parameter defaults.
Connector for Petrel 2020
With Paradise 3.4, geoscientists and engineers using Petrel and Paradise continue to enjoy straightforward drag-and-drop, bi-directional transfer of files when using Petrel version 2020.
KEY TECHNOLOGIES IN PARADISE
Generate attributes to extract meaningful geological information and as input into machine learning analysis
Identify attributes having the highest variance and contribution among a set of attributes in a geologic setting
Classify multiple attribute volumes simultaneously utilizing Self-Organizing Maps (SOM), an unsupervised machine learning process
Display the Neural Classes (topology) and their associated colors resulting from Multi-Attribute Classification that indicate the distribution of related facies
Capture facies based on distinctive seismic patterns using Convolutional Neural Network (CNN) deep learning technology
Produce fault probability volumes based on existing fault engines (models) or from interpreter-guided, trained engines
Compare machine learning classification results and other seismic attributes to traditional well logs
Generate geometric and spectral decomposition attributes on a cluster of compute nodes in a fraction of the time on a single machine
Write and save scripts that can be run by the Paradise AI engine using over 600 geoscience, machine learning, and data analysis commands