Principal component neural network for seismic pattern analysis

The neural network using an unsupervised generalized Hebhian algorithm (GHA) is adopted to find the principal eigenvectors of a covariance matrix in different kinds of seismograms. Principal components analysis (PCA) using the neural net of GHA allows one to extract information of seismic reflection layers and uniform neighboring traces. For PCA. a theorem is proposed that adding extra point along the direction of the existing eigenvector can enhance thai eigenvector. This theorem is applied to the fault analy sis and a real seismogram at Mississippi Canyon. The results of PCA using neural network can improve the seismic interpretation.