Implementation of the Principle Phase Decomposition Algorithm

Abstract

This paper outlines the implementation details and enhancements of a previously described new concept in blind seismic deconvolution that is referred to as principle phase decomposition (PPD). A requirement of the PPD algorithm is for the investigator to determine the seismogram's dominant frequency (DF) and corresponding principle phase components (PPCs). Once these parameters are estimated, a hybrid Rao-Blackwellized particle filter and a hidden Markov model (HMM) filter are utilized to separate the potentially time-variant overlapping source wavelets. A variation of the PPD algorithm that is referred to as the PPD wavelet extraction (PPD-WE) technique addresses the requirement of estimating the seismogram's DF and PPCs. This paper describes in detail the PPD-WE algorithm where the overlapping source wavelets are sequentially and chronologically extracted from the seismogram under analysis. A HMM filter is described which facilitates in the simultaneous estimation of the DF and the corresponding phase of the source wavelet to be extracted within the PPD-WE algorithm. In addition, the utilization of the PPD-WE algorithm within standard frequency-domain deconvolution techniques is outlined