Skip to main content
A detailed picture of Haiti’s seismicity given by deep learning and template matching

A detailed picture of Haiti’s seismicity given by deep learning and template matching

This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.

Downloads

Download Preprint

Authors

Miguel Neves , Quentin Bletery , Françoise Courboulex, David Ambrois, Jérôme Chèze, Tony Monfret, Steeve Symithe, Sylvert Paul, Louis de Barros, Bryan Raimbault, Eric Calais 

Abstract

Haiti regularly experiences destructive earthquakes, but seismic monitoring in the region has historically been limited. Recent deployments of citizen-hosted RaspberryShake seismometers and temporary seismic deployment following the 2021 Mw 7.2 earthquake provide new data to study the region’s seismotectonics. However, high noise levels at many stations, in particular the RaspberryShake ones, limit detection, hence the fault imaging capability of these instruments. This study explores the use of a Deep Learning denoising algorithm, DeepDenoiser, to improve their seismic signal and earthquake detection capabilities. We find that DeepDenoiser raises the average signal-to-noise ratio of seismic signals by 4.7 dB and increases earthquake detections, but also raises false detections when using STA/LTA and a Deep Learning detection method. Template matching, however, when combined with DeepDenoiser, yields more true detections and fewer false detections than traditional band-pass filtered waveforms. This suggests that DeepDenoiser is better suited for retrospective studies than for real-time applications. Using DeepDenoiser and template matching, we compile a 2-year, high-resolution earthquake catalog for Haiti containing about 3 times the number of events of the original catalog. The improved catalog furthers our understanding of the 2021 Mw 7.2 earthquake sequence, highlighting particularly clearly the segmented nature of the aftershock distribution with a generally NE–dipping cluster in the east that coincides with the hypocenter and first reverse phase of the rupture, and a series of aftershocks farther west that coincide with the mostly strike-slip phase of the rupture. The improved catalog also reveals fluid-induced offshore seismic swarms in the Jérémie basin and active seismicity below Lake Enriquillo in the Dominican Republic. This catalog advances our knowledge of the region seismic activity and provides further opportunities to study the larger regional tectonic context.

DOI

https://doi.org/10.31223/X5K47Q

Subjects

Earth Sciences, Geophysics and Seismology, Physical Sciences and Mathematics

Keywords

Seismology, Deep learning, Haiti, Hispaniola, 2021 Nippes earthquake, Fluid driven seismicity, Earthquake Detection

Dates

Published: 2026-01-20 14:08

Last Updated: 2026-01-20 14:08

License

No Creative Commons license

Additional Metadata

Conflict of interest statement:
None

Data Availability (Reason not available):
The detection and relocated catalogs resulting from this study will be published as supplementary files and can in the meantime be requested to the first author (migueljgneves@gmail.com). The Ayiti-seismes earthquake catalog and data from the HY network are available at the Ayiti-seismes platform (https:// ayiti.unice.fr/ayiti-seismes). Data from networks AY, CN (Natural Resources Canada, 1975), CU (Albuquerque Seismological Laboratory (ASL)/USGS, 2006), DR (National Seismological Centre, 1998), LO (Instituto Politecnico Loyola, 2012) can be accessed through IRIS Web Services (https://service.iris.edu/). Z2 network data will be available through IRIS Web Services in October 2026.

Metrics

Views: 65

Downloads: 6