Method for the automated editing of seismic traces using an adaptive network
First Claim
1. A method for operating a computer as an adaptive network to classify each of a plurality of seismic traces as useful or noisy, according to noise amplitude of in each trace, each of said traces corresponding to seismic vibrations detected responsive to a seismic source input signal, comprising:
- retrieving stored data representative of a first of said plurality of traces;
generating a frequency domain amplitude spectrum for said first trace from said retrieved data;
presenting data from said frequency domain amplitude spectrum to input nodes of said adaptive network, said adaptive network indicating, responsive to said frequency domain amplitude spectrum data, a classification of said first trace as useful or noisy; and
storing the result of said presenting step.
1 Assignment
0 Petitions
Accused Products
Abstract
An adaptive, or neural, network and a method of operating the same is disclosed which is particularly adapted for performing seismic trace editing for seismic shot records. The adaptive network is first trained according to the generalized delta rule. The disclosed training method includes backpropagation is performed according to the worst case error trace, including adjustment of the learning and momentum factors to increase as the worst case error decreases. Slow convergence regions are detected, and methods applied to escape such regions including restoration of previously trimmed dormant links, renormalization of the weighting factor values, and the addition of new network layers with links between nodes that skip the hidden layer. After the training of the network, data corresponding to a Discrete Fast Fourier Transform of each trace, and to certain other attributes of the trace and adjacent traces thereto, are presented to the network. The network classifies the trace as good or noisy according to the inputs thereto, and to the weighting factors therewithin, such classification useful for ignoring noisy traces in subsequent data analysis. The analysis may be repeated for all of the traces in the shot record, and in multiple shot records.
63 Citations
20 Claims
-
1. A method for operating a computer as an adaptive network to classify each of a plurality of seismic traces as useful or noisy, according to noise amplitude of in each trace, each of said traces corresponding to seismic vibrations detected responsive to a seismic source input signal, comprising:
-
retrieving stored data representative of a first of said plurality of traces; generating a frequency domain amplitude spectrum for said first trace from said retrieved data; presenting data from said frequency domain amplitude spectrum to input nodes of said adaptive network, said adaptive network indicating, responsive to said frequency domain amplitude spectrum data, a classification of said first trace as useful or noisy; and storing the result of said presenting step. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method of operating an adaptive network in a computing apparatus, said apparatus including stored data representative of a seismic shot record including a plurality of traces, said stored data corresponding to time domain data for each of said traces, comprising:
-
retrieving a portion of said stored data corresponding to a plurality of traces; generating a frequency domain amplitude spectrum for a first trace from said retrieved data; calculating a first attribute value for said first trace from said retrieved data; applying data from said frequency domain amplitude spectrum and said first attribute value to a computer program having the form of an adaptive network, said adaptive network generating outputs for indicating whether the trace associated with the data presented to its inputs is useful or is noisy, said indication based upon the setting of adaptive network weighting factors according to the generalized delta rule from sample useful and noisy traces; and storing the outputs of said adaptive network for said first trace. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20)
-
Specification