# Probing slow earthquakes with deep learning

## TL;DR

This paper demonstrates that deep learning can effectively detect slow earthquakes and tremor from seismic data, providing insights into slow slip behavior and its potential universality across different fault zones.

## Contribution

The study introduces a convolutional neural network that detects tremor and slow slip, generalizes across multiple fault zones, and offers a new proxy for quantifying slow slip rates.

## Key findings

- Deep neural network accurately detects tremor in Cascadia.
- Model generalizes to other subduction zones and faults.
- Provides a proxy for slow slip rate quantification.

## Abstract

Slow earthquakes may trigger failure on neighboring locked faults that are stressed enough to break, and slow slip patterns may evolve before a nearby great earthquake. However, even in the clearest cases such as Cascadia, slow earthquakes and associated tremor have only been observed in intermittent and discrete bursts. By training a convolutional neural network to detect known tremor on a single seismic station in Cascadia, we isolate and identify tremor and slip preceding and following known larger slow events. The deep neural network can be used for the detection of quasi-continuous tremor, providing a proxy that quantifies the slow slip rate. Furthermore, the model trained in Cascadia recognizes tremor in other subduction zones and also along the San Andreas Fault at Parkfield, suggesting a universality of waveform characteristics and source processes, as posited from experiments and theory.