Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue (Data Paper) Proceedings of the 40th International Conference on Machine Learning Année : 2023

Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data

Résumé

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.
Fichier principal
Vignette du fichier
siahkoohi23a.pdf (6.4 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04177840 , version 1 (06-08-2023)

Identifiants

Citer

Ali Siahkoohi, Rudy Morel, Maarten V. de Hoop, Erwan Allys, Grégory Sainton, et al.. Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data. Proceedings of the 40th International Conference on Machine Learning, 2023, Proceedings of the 40 th International Conference on Machine Learning, Honolulu, 202, pp.31754-31772. ⟨hal-04177840⟩
31 Consultations
5 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More