[S-SS03] New trends in data acquisition, analysis and interpretation of seismicity

[SSS03-05] Detection of millimiter-scale slow slip events on continental faults in InSAR time series using deep learning

★Invited Papers

*Bertrand Rouet-Leduc¹, Romain Jolivet², Sylvain Michel², Claudia Hulbert³ (1.DPRI, Kyoto University, 2. Laboratoire de Geologie, Ecole Normale Superieure, France, 3.Geolabe, USA)

Keywords:Slow earthquakes, Slow slip event, InSAR, Deep learning, Machine learning

Faults can accommodate stress in a variety of slip modes, from dynamic rupture to slow slip events and aseismic slip. Among these slip modes, slow slip events and often-accompanying tremor remain the most elusive and poorly understood.

Unraveling the interactions between slip modes is at stake: while laboratory experiments point to aseismic nucleation generally preceding dynamic rupture, observations in the field are far from systematic, and more the exception than the rule.

However, the difficulty in detecting transient slow slip events, either seismically or geodetically, points to a possible observational gap that may explain the rarity of slow deformation detected prior to dynamic earthquakes.

In this presentation, the use of machine learning to improve the detection of slow slip events will be explored, as a tool to fill this observational gap, both in seismic data and in geodetic data.