Lg depth estimation and ripple fire characterization using artificial neural networks

The authors demonstrate how artificial neural networks (ANNs) can be applied to characterizing seismic sources using high-frequency regional seismic data. The authors take the novel approach of using ANNs as a research tool for obtaining seismic source information, specifically depth of focus for earthquakes and ripple-fire characteristics for economic blasts, rather than as just a feature classifier between earthquake and explosion populations. The authors suggest that ANNs have potential applications to seismic event characterization and identification, beyond just a feature classifier. The Lg spectral matrix provides a hidden discriminant in that it appears to be sensitive to depth of focus effects, which can be recognized by the ANN. ANNs can also even recognize ripple-fire patterns not used in training. The results of this study indicate that an ANN should be evaluated as part of an operational seismic event identification system