Tremor Waveform Denoising and Automatic Location with Neural Network Interpretation

TL;DR

This paper introduces a neural network-based method for denoising and locating tectonic tremors within seismic noise, enhancing detection capabilities and waveform interpretation in the Cascadia subduction zone.

Contribution

The study presents a novel neural network approach combining attribution and standard array techniques to improve tremor detection, denoising, and localization from seismic data.

Findings

Successfully identified tremor patches consistent with existing catalogs.

Denoised waveforms travel at local crust and mantle wavespeeds.

Detected more tremors than previous catalogs.

Abstract

Active faults release tectonic stress imposed by plate motion through a spectrum of slip modes, from slow, aseismic slip, to dynamic, seismic events. Slow earthquakes are often associated with tectonic tremor, non-impulsive signals that can easily be buried in seismic noise and go undetected. We present a new methodology aimed at improving the detection and location of tremors hidden within seismic noise. After identifying tremors with a classic convolutional neural network, we rely on neural network attribution to extract core tremor signatures and denoise input waveforms. We then use these cleaned waveforms to locate tremors with standard array-based techniques. We apply this method to the Cascadia subduction zone, where we identify tremor patches consistent with existing catalogs. In particular, we show that the cleaned signals resulting from the neural network attribution analysis correspond to a waveform traveling in the Earth's crust and mantle at wavespeeds consistent with local estimates. This approach allows us to extract small signals hidden within the noise, and therefore to locate more tremors than in existing catalogs.