Record details

    Statistical interpretation of WEBNET seismograms by artificial neural nets
Statement of responsibility
    Axel Plešinger, Bohuslav Růžek, Alena Boušková
    Boušková, Alena
    Plešinger, Axel
    Růžek, Bohuslav
Source title - serial
    Studia geophysica et geodaetica
    Roč. 44, č. 2
    s. 251-271
    10 obr., 4 tab., 13 bibl.
    Zkr. název ser.: Stud. geophys. geod. (Praha)
Subject group
    analýza statistická
    měření seizmické
    podkrušnohorské pánve
    sedimenty klastické
    zdroj seizmicity
Geographical name
Abstract (in english)
   We employed multilayer perceptrons (MLP), self organizing feature maps (SOFM), and learning vector organization (LVQ) to reveal and interpret statistically significant features of different categories of waveform parameters vectors extracted from three-component WEBNET velocigrams. In this contribution we present and discuss in a summarizing manner the results of (i) SOFM classifications and MLP discrimination between microearthquakes and explosions on the basis of single-station spectral and amplitude parameter vectors, (ii) SOFM/LVQ recognition of initial onset polarities from PV-waveforms, and (iii) a source mechanism study of the January 1997 microearthquake swarm based on SOFM classification of combined multi-station PV-onset polarity and SH/PV aplitude ratio (CPA) data.
   Unsupervised SOFM classification of 497 NKC seismograms revealed that the best discriminants are pure spectra parameter vectors for the recognition of microearthquakes (reliability 95 with 30 spectral parameters), and mixed amplitude and spectral parameter vectors for the recognition of explosions (reliability 98 with 41 amplitude and 30 spectral parameters). The optimal MLP, trained with the standard backpropagation error method by one randomly selected half of a set of 312 mixed (7 amplitude and 7 spectral single-station (NKC) microearthquake half and explosion parameter vectors and tested by the other half-set, and vice versa, correctly classified, on average, 99 of all events
    Česká geologická služba
Contributor code
    ČGS (UNM)
Source format
Entered date
    31. 3. 2008
Import date
    8. 8. 2012