GlitchNet: A Glitch Detection and Removal System for SEIS Records Based on Deep Learning

Wuchuan Xu, Qiwen Zhu, Li Zhao

Seismological Research Letters 2022 article cited by 20

importance 5/10 solved Seismology and Earthquake Studies planetary seismology stage: research

Problem

Glitches, a common type of noise, contaminate continuous seismic data recorded by the SEIS instrument on Mars during the InSight mission.

Why it matters

Clean seismic records are essential for extracting science from Mars interior data.

What the AI did

A five-layer CNN detects glitches, and a deep autoencoder constructs the glitch waveform that is subtracted from the raw record; combined as GlitchNet, trained on datasets built with existing algorithms.

Results

Better glitch detection and removal performance with much higher computational efficiency than existing methods (no numbers stated).

Impact

The abstract claims the system outperforms existing methods on SEIS very broadband records, published in a credible seismology venue.

Record

Venue	Seismological Research Letters
Published	2022
Work type	article
Authors	Wuchuan Xu, Qiwen Zhu, Li Zhao
Citations	20 (OpenAlex, at import time)
References	41
Model or method	GlitchNet: five-layer CNN plus deep autoencoder
Organization	not stated in source
Primary source	https://doi.org/10.1785/0220210361
Open access	closed
Keywords	glitch detection, deep learning, Mars, InSight, seismology, autoencoder

Importance rating

5 / 10

real but narrower advance

Clean Mars seismic data enables interior science for the InSight mission; important but niche planetary-science data processing, no stated broader scale.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Physics & Astronomy

#	Paper	Year	Citations	Importance
1	Magnetic control of tokamak plasmas through deep reinforcement learning Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan...	2022	739	7
2	Solving the quantum many-body problem with artificial neural networks Giuseppe Carleo, Matthias Troyer	2017	2,205	7
3	Learning high-accuracy error decoding for quantum processors Johannes Bausch, Andrew Senior, Francisco J. H. Heras, Thomas Edlich,...	2024	90	7
4	Optimizing Quantum Error Correction Codes with Reinforcement Learning Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Brie...	2019	158	7
5	Machine-learning-assisted correction of correlated qubit errors in a topological code Paul Baireuther, Thomas E. O’Brien, Brian Tarasinski, C. W. J. Beenakk...	2018	141	7