Phase identification and attribute analysis of broadband seismograms at far-regional distances

A trained analyst can frequently provide a rapid assessment of a seismic record and provide identification for many seismic phases. For digital data a challenge is to find methods (or combinations of methods) which can provide equivalent levels of phase identification and attribute analysis. Until now, there have been few discussions on phase attribute analysis for broadband records, even though the character of the major phases has been recognised several decades ago. We introduce a combination of four simple methods into the analysis of broadband seismograms so as to provide a means of improving phase recognition and the full use of broadband information for far-regional distances where the seismograms are particularly complex (because of the influence of the upper mantle discontinuities). For arrival detection we can employ the energy ratios of the short term behaviour to the long-term trend, using the vertical component and horizontal components of unrotated seismic records. We also use auto-regressive analysis to endeavour to separate broadband records into three parts: the seismic signal, microseismic noise and white noise. The higher order auto- and cross-correlation coefficient (representing the similarity of waveform) can be used to identify the presence of seismic phases, by avoiding the influence of the relatively low order correlation of microseismic noise. For each broadband 3-component record a set of complex traces are constructed and then a variety of definitions of instantaneous phase and frequency can be exploited to separate the behaviour of signal and noise. The complex traces can also be used for polarisation analysis. The changes in the character of the eigenvectors are particularly helpful for recognising the phases of broadband records in the far-regional range. The individual methods are quite powerful but when used in combination can provide a very effective means of phase characterisation.