Versions Compared

Version Old Version 6 New Version 7
Changes made by

ian macleod (Deactivated)

ian macleod (Deactivated)

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

...


Page Properties


SummaryClassification of multi-variate data using Self-Organizing Maps (SOM), an AI technique. A Geosoft Python script that runs from Oasis montaj and applies the technique to a Geosoft database is part of this project.
Researchers

ian macleod (Deactivated)
Rob Ellis (Deactivated)
@Telma Aisengart

Githubhttps://github.com/GeosoftInc/Geoscience/tree/master/Open%20research/self_organizing_maps
Publications

Quantitative Magnetization Inversion

Self-Organizing Maps applied to Magnetization Vector Inversion

Application of SOM technique to the Magnetization vector

See alsoCracknell, 2014, a SOM analysis of Australia



Installation

  1. Install Oasis Montaj.
  2. Install Python (see https://github.com/GeosoftInc/gxpy/wiki/Python-menu-for-Geosoft-Desktop)
  3. Copy *.py files from 
  4. Set environment variable MYPYFILES=C:\python\geosoft"
  5. Create a database with multivariate data, and display the data channels to be analysed, and only those channels.
  6. Run the GX python.gx, which will in turn let you select the "som_om.py" file from your c:/python/geosoft folder. The first time you run this GX you will also need to locate your python 3.4 python.exe file.


Usage Notes

This GX analyses multivariate data by grouping data into statistically meaningful groupings using SOM neural-network analysis. The technique is described here:

http://en.wikipedia.org/wiki/Self-organizing_map

Up to 16 separate data channels can be analysed. The first three channels are used to colour-code the resulting SOM neural network report. The report provides a simple visual impression of the classifications.

The size of the neural network is the square-root of the number of classifications, which can be any of 4,6,16,25,36,49,etc… Two new channels are added (or replaced) in the database:

Class – the classifications, 0 to number of classifications-1EuD – Euclidian distance of the point from the assigned neuron class, which is the closest based on Euclidian distance.

If an anomalous percent above 0 is specified, the percent of data that is furthest from the network (by Euclidian distance) is re-classified a second time on its own into a second SOM network of the same dimension such that there will be twice as many classes. For example, choosing 16 classifications and 5% anomalous data will result in 32 classes (16+16) where classes 0 to 15 capture the 95% of data that most closely fits the original network, and classes 16 to 31 are the most extreme 5% reclassified in their own network.

To work with gridded or voxel data:

  1. Export a grid or voxel to a new database.
  2. Sample other grids/voxels into new channels of the database.
  3. Run the SOM analysis.
  4. Save the "Class" channel as a grid or voxel.
  5. Imagination encouraged!

For example, you can classify MVI results based on the x,y,z vector directions and the amplitude, which kind of double-weights the amplitude in the analysis. Because the directions can range + or -, the amplitude is scalar, and all dimensions are likely reasonably and meaningfully scaled relative to each other then no normalization is necessary. The process would be:

  1. Create a database from the amplitude voxel.
  2. Sample the x, Y and Z directions into mx,my,mz channels.
  3. Run a SOM, dimension 9 (or 16), anomalous percent 5.
  4. Convert Class channel to voxel and view.
  5. Clip the data to above 9 (or 16), and this is the SOM of the anomolous locations.