Automatic detection for a comprehensive view of Mayotte seismicity

Abstract

The seismic crisis that began in May, 2018 off the coast of Mayotte announced the onset of a volcanic eruption that started two months later 50 km southeast of the island. This seismicity has since been taken as an indicator of the volcanic and tectonic activity in the area. In response to this activity, a network of stations was deployed on Mayotte over the past three years. We used the machine learning-based method PhaseNet to re-analyze the seismicity recorded on land since March 2019. We detect 50,512 events compared to around 6508 manually picked events between March 2019 and March 2021. We locate them with NonLinLoc and a locally developed 1-D velocity model. While eruptions are often monitored through the analysis of Volcano-Tectonic (VT) seismicity (2–40 Hz), we focus on the lower frequency, Long Period (LP) earthquakes (0.5–5 Hz), which are thought to be more directly related to fluid movement at depth. In Mayotte, the VT events are spread between two clusters, whereas the LP events are all located in a single cluster in the bigger proximal VT cluster, at depths ranging from 25 to 40 km. Moreover, while the VT earthquakes of the proximal cluster occur continuously with no apparent pattern, LP events occur in swarms that last for tens of minutes. We show that during the swarms, LP events generally migrate downward at a speed of 5 m/s. While these events do not appear directly linked to upward fluid migration, their waveform signature could result from propagation through a fluid-rich medium. They occur at a different location than VT earthquakes, also suggesting a different origin which could be linked to the Very Long Period events (VLP) observed above the LP earthquakes in Mayotte.

Keywords

• Volcano
• Mayotte
• Seismicity
• Machine learning
• Long Period
• Volcano-Tectonic
• Phase picking