Method for processing seismic measured data with a neuronal network
AssigneeHenning Trappe
InventorsHenning Trappe, Carsten Hellmich, Marc Föll
Life of this patent
Estimating the term…
Abstract
The invention relates to a method for processing a 3-D measurement data set provided with seismic attributes, by means of a neural network, whereby a self-organizing map is trained with selected training data, and the data to be examined are classified according to the self-organizing map. In this connection, the measurement data are processed by way of sub-volumes comprising a spatial environment of each sample. The classification is stored in a result data set, and displayed, for example in a two-dimensional map (FIG. 3).
Claims23
A method for processing and classifying a 3-D measurement data set provided with seismic attributes, by means of a neural network, comprising:
- training a self-organizing map by selecting training data, said training data being randomly selected from a measurement data set;
- and
- classifying data to be investigated according to the self-organizing map wherein for each measurement data point, of a considered measurement data volume, a classification number is assigned, which is an ordinal number of a winner neuron in the neural network;
- wherein the measurement data are processed in the form of sub-volumes, comprising a spatial environment of each measurement data point.
Dependencies are inferred from the claim text.