Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier

The deformation of slow-moving landslides developed in clays induces endogenous seismicity of mostly low-magnitude events (M-L<1). Long seismic records and complete catalogs are needed to identify the type of seismic sources and understand their mechanisms. Manual classification of long records is time-consuming and may be highly subjective. We propose an automatic classification method based on the computation of 71 seismic attributes and the use of a supervised classifier. No attribute was selected a priori in order to create a generic multi-class classification method applicable to many landslide contexts. The method can be applied directly on the results of a simple detector. We developed the approach on the seismic network of eight sensors of the Super-Sauze clay-rich landslide (South French Alps) for the detection of four types of seismic sources. The automatic algorithm retrieves 93% of sensitivity in comparison to a manually interpreted catalog considered as reference.