McCormack, Michael D.

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.

McCormack, Michael D.; Rock, Alan D.

An adaptive, or neural, network and a method of operating the same is disclosed which is particularly adapted for performing first break analysis for seismic shot records. The adaptive network is first trained according to the generalized delta rule. The disclosed training method includes selection of the seismic trace with the highest error, where the backpropagation is performed according to the error of this worst trace. The learning and momentum factors in the generalized delta rule are adjusted according to the value of the worst error, so that the learning and momentum factors increase as the error decreases. The training method further includes detection of slow convergence regions, and methods for escaping such regions including restoration of previously trimmed dormant links, renormalization of the weighting factor values, and the addition of new layers to the network. The network, after the addition of a new layer, includes links between nodes which skip the hidden layer. The error value used in the backpropagation is reduced from that actually calculated, by adjusting the desired output value, in order to reduce the growth of the weighting factors. After the training of the network, data corresponding to an average of the graphical display of a portion of the shot record, including multiple traces over a period of time, is provided to the network. The time of interest of the data is incremented until such time as the network indicates that the time of interest equals the first break time. The analysis may be repeated for all of the traces in the shot record.