Internet Explorer 9 and Safari users must enable TLS in their browser settings (The new Ocean website uses TLS for enhanced security). Accept
* Internet Explorer version 9: Enable TLS versions 1.0. 1.1 and 1.2 in your Browser settings (Internet options > Advanced > Settings > Security).
* Safari: Enable TLS versions 1.0. 1.1 and 1.2 in your Browser settings (Preferences > Advanced Icon > Change Settings > Advanced Tab > Settings).


Ocean does not support Internet Explorer versions 8 and below. Get Latest Version
If you still have trouble, you should also clear your browser cache: press Shift-Ctrl-Delete [any browser, except Safari] and delete all items.
Further questions can be submitted via Contact Us
IPLAB Kohonen1D/2D/3D Classification2D
By IPLAB LLC
Plug-in Attributes
Platform:
Petrel
Lifecycle
Exploration
Challenges:
Unconventional Heavy Oil | Carbonates | Deepwater Exploration and Production | Unconventional Shale
ECCN:
Russia origin, EAR99
Version
  • 2017 | 2018
Supporting Documents
Installation Guide
Release Notes
User Manual
Others
Overview
Surface properties or seismic waveform classification using Kohonen 1D, 2D, and 3D neural network. The plug-in can be used for unsupervising classification via a set of surface attributes or seismic cube waveform and based on Kohonen SOM 1D, 2D, or 3D. The results of this plug-in are maps (surface attributes).
Specifications
1D Kohonen neural network will create one-index classes. 2D Kohonen neural network will create two-index classes and requires RGB mix visualization. 3D Kohonen neural network will create three-index classes and requires RGB mix visualization. During learning and calculation stages, the plug-in uses parallel calculation based on all available CPU cores. It helps to perform calculations for 3D Kohonen and saves significant time. Using an RGB mix for Petrel platform maps allows generating user-defined template color tables with specific number of classes for 3D or 2D Kohonen neural network results.
Features
  • Using Kohonen 2D or 3D projection allows for better showing object positions in multidimensional space
  • RGB blending of 2D or 3D neural network projections potentially permits a more accurate geological facies interpretation
Additional Information
Allows using a defined set of surface properties for classification. Optionally, it can be used for seismic waveform classification based on seismic cubes (one or several) and with layer definition (top and bottom surfaces).