loading page

PolarCAP -- A Deep Learning approach for First Motion Polarity Classification of Earthquake Waveforms
  • +4
  • Megha Chakraborty,
  • Claudia Quinteros Cartaya,
  • Wei Li,
  • Johannes Faber,
  • Georg Rümpker,
  • Horst [email protected],
  • Nishtha Srivastava
Megha Chakraborty
Frankfurt Institute for Advanced Studies
Author Profile
Claudia Quinteros Cartaya
Frankfurt Institute for Advanced Studies
Author Profile
Wei Li
Frankfurt Institute for Advanced Studies
Author Profile
Johannes Faber
Frankfurt Institute for Advanced Studies
Author Profile
Georg Rümpker
Goethe University Frankfurt
Author Profile
Frankfurt Institute for Advanced Studies
Author Profile
Nishtha Srivastava
Frankfurt Institute for Advanced Studies

Corresponding Author:[email protected]

Author Profile

Abstract

The polarity of first P-wave arrivals plays a significant role in the effective determination of focal mechanisms specially for smaller earthquakes. Manual estimation of polarities is not only time-consuming but also prone to human errors. This warrants a need for an automated algorithm for first motion polarity determination. We present a deep learning model - PolarCAP that uses an autoencoder architecture to identify first-motion polarities of earthquake waveforms. PolarCAP is trained in a supervised fashion using more than 130,000 labelled traces from the Italian seismic dataset (INSTANCE) and is cross-validated on $\sim$22,000 traces to choose the most optimal set of hyperparameters. We obtain an accuracy of 0.98 on a completely unseen test dataset of almost 33,000 traces. Furthermore, We check the model generalizability by testing it on the datasets provided by previous works and show that our model achieves a higher recall on both positive and negative polarities.