Machine learning and marsquakes: a tool to predict atmospheric-seismic noise for the NASA InSight mission

This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: This is version 1 of this Preprint.

Add a Comment

You must log in to post a comment.


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


Download Preprint


Alexander Stott, Raphael Garcia, Armand Chédozeau, Aymeric Spiga, Naomi Murdoch, Baptiste Pinot, David Mimoun, Constantinos Charalambous, Anna Horleston, Scott King, Taichi Kawamura, Nikolaj Dahmen, Salma Barkaoui, Philippe lognonne, Bruce Banerdt


The SEIS experiment on the NASA InSight mission has catalogued hundreds of marsquakes so far. However, the detectability of these events is controlled by the weather which generates seismic noise. This affects the catalogue on both diurnal and seasonal scales. We propose to use machine learning methods to fit the wind, pressure and temperature data to the seismic energy recorded in the 0.4-1 Hz and 2.2-2.6 Hz bandwidths to examine low and high frequency event categories respectively. We implement gaussian process regression and neural network models for this task. This approach provides the relationship between the atmospheric state and seismic energy. The obtained seismic energy estimate is used to calculate signal to noise ratios (SNR) of marsquakes for multiple bandwidths. We can then demonstrate the presence of low frequency energy separate to the noise level during several events predominantly categorised as high frequency, suggesting a continuum in event spectra distribution. A method to detect marsquakes is implemented whereby a variable threshold is calculated for the subtraction of the predicted noise from the observed signal. This algorithm finds 32 previously undetected marsquakes, with another 34 possible candidates. Furthermore, an analysis of the detection algorithm's variable threshold provides an empirical estimate of marsquake detectivity. This suggests that the largest events would be seen almost all the time, the median size event 45-50% of the time and smallest events 5-20% of the time.



Geophysics and Seismology, Planetary Geophysics and Seismology


machine learning, Planetary Interiors, seismic noise, Extraterrestrial seismology


Published: 2022-04-27 10:34


CC BY Attribution 4.0 International

Additional Metadata

Data Availability (Reason not available):
SEIS data are referenced at\_2016. The Mars Quake service (MQS) catalogue of events used in this contribution is the Mars Seismic Catalogue, InSight Mission, V9 acknowledging ETHZ, IPGP, JPL, ICL, ISAE-Supaero, MPS, and the University of Bristol. It is available at