Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data

Ali Siahkoohi, Rudy Morel, Maarten V. De Hoop, Erwan Allys, Gregory Sainton, Taichi Kawamura
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31754-31772, 2023.

Abstract

Source separation involves the ill-posed problem of retrieving a set of source signals that have been observed through a mixing operator. Solving this problem requires prior knowledge, which is commonly incorporated by imposing regularity conditions on the source signals, or implicitly learned through supervised or unsupervised methods from existing data. While data-driven methods have shown great promise in source separation, they often require large amounts of data, which rarely exists in planetary space missions. To address this challenge, we propose an unsupervised source separation scheme for domains with limited data access that involves solving an optimization problem in the wavelet scattering covariance representation space—an interpretable, low-dimensional representation of stationary processes. We present a real-data example in which we remove transient, thermally-induced microtilts—known as glitches—from data recorded by a seismometer during NASA’s InSight mission on Mars. Thanks to the wavelet scattering covariances’ ability to capture non-Gaussian properties of stochastic processes, we are able to separate glitches using only a few glitch-free data snippets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-siahkoohi23a, title = {Unearthing {I}n{S}ights into Mars: Unsupervised Source Separation with Limited Data}, author = {Siahkoohi, Ali and Morel, Rudy and De Hoop, Maarten V. and Allys, Erwan and Sainton, Gregory and Kawamura, Taichi}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {31754--31772}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/siahkoohi23a/siahkoohi23a.pdf}, url = {https://proceedings.mlr.press/v202/siahkoohi23a.html}, abstract = {Source separation involves the ill-posed problem of retrieving a set of source signals that have been observed through a mixing operator. Solving this problem requires prior knowledge, which is commonly incorporated by imposing regularity conditions on the source signals, or implicitly learned through supervised or unsupervised methods from existing data. While data-driven methods have shown great promise in source separation, they often require large amounts of data, which rarely exists in planetary space missions. To address this challenge, we propose an unsupervised source separation scheme for domains with limited data access that involves solving an optimization problem in the wavelet scattering covariance representation space—an interpretable, low-dimensional representation of stationary processes. We present a real-data example in which we remove transient, thermally-induced microtilts—known as glitches—from data recorded by a seismometer during NASA’s InSight mission on Mars. Thanks to the wavelet scattering covariances’ ability to capture non-Gaussian properties of stochastic processes, we are able to separate glitches using only a few glitch-free data snippets.} }
Endnote
%0 Conference Paper %T Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data %A Ali Siahkoohi %A Rudy Morel %A Maarten V. De Hoop %A Erwan Allys %A Gregory Sainton %A Taichi Kawamura %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-siahkoohi23a %I PMLR %P 31754--31772 %U https://proceedings.mlr.press/v202/siahkoohi23a.html %V 202 %X Source separation involves the ill-posed problem of retrieving a set of source signals that have been observed through a mixing operator. Solving this problem requires prior knowledge, which is commonly incorporated by imposing regularity conditions on the source signals, or implicitly learned through supervised or unsupervised methods from existing data. While data-driven methods have shown great promise in source separation, they often require large amounts of data, which rarely exists in planetary space missions. To address this challenge, we propose an unsupervised source separation scheme for domains with limited data access that involves solving an optimization problem in the wavelet scattering covariance representation space—an interpretable, low-dimensional representation of stationary processes. We present a real-data example in which we remove transient, thermally-induced microtilts—known as glitches—from data recorded by a seismometer during NASA’s InSight mission on Mars. Thanks to the wavelet scattering covariances’ ability to capture non-Gaussian properties of stochastic processes, we are able to separate glitches using only a few glitch-free data snippets.
APA
Siahkoohi, A., Morel, R., De Hoop, M.V., Allys, E., Sainton, G. & Kawamura, T.. (2023). Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:31754-31772 Available from https://proceedings.mlr.press/v202/siahkoohi23a.html.

Related Material