Machine Learning Reveals the Seismic Signature of Eruptive Behavior at Piton de la Fournaise Volcano

International audienceVolcanic tremor is key to our understanding of active magmatic systems, but due to its complexity, there is still a debate concerning its origins and how it can be used to characterize eruptive dynamics. In this study we leverage machine learning techniques using 6 years of continuous seismic data from the Piton de la Fournaise volcano (La Réunion island) to describe specific patterns of seismic signals recorded during eruptions. These results unveil what we interpret as signals associated with various eruptive dynamics of the volcano, including the effusion of a large volume of lava during the August-October 2015 eruption as well as the closing of the eruptive vent during the September-November 2018 eruption. The machine learning workflow we describe can easily be applied to other active volcanoes, potentially leading to an enhanced understanding of the temporal and spatial evolution of volcanic eruptions. Plain Language Summary A good understanding of volcanic activity is key to managing volcanic hazards resulting from eruptive activity. Volcanic tremor is a continuous seismic signal often seen during eruptions associated with the flow of magma through the volcano and is thus an extremely useful tool in characterizing the progression and phases of eruptions. In this study we study this signal at the Piton de la Fournaise volcano, on La Réunion island. Using machine learning algorithms, we investigate characteristics of this signal emitted by the volcano during eruptions to reveal the fundamental frequency at which it occurs, as well as changes in eruptive state that occur during some eruptions in our data set. This workflow may be applied to other volcanos to further our understanding of eruptive dynamics