Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data

TL;DR

This paper introduces an unsupervised source separation method using wavelet scattering covariances, enabling the removal of glitches from Mars seismometer data with limited samples, advancing planetary data analysis.

Contribution

The paper presents a novel unsupervised source separation approach based on wavelet scattering covariances tailored for limited data scenarios in planetary missions.

Findings

Successfully separated glitches from Mars seismometer data

Achieved effective source separation with minimal data snippets

Demonstrated the method's ability to capture non-Gaussian properties

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$\unicode{x2014}$an interpretable, low-dimensional representation of stationary processes. We present a real-data example in which we remove transient, thermally-induced microtilts$\unicode{x2014}$known as glitches$\unicode{x2014}$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.