Optimal frequency-domain analysis for spacecraft time series: Introducing the missing-data multitaper power spectrum estimator

TL;DR

This paper introduces a missing-data multitaper power spectrum estimator tailored for spacecraft time series with gaps, demonstrating its effectiveness in detecting stellar oscillations and rotation profiles without iterative fitting.

Contribution

The paper adapts the missing-data multitaper power spectrum estimator for spacecraft data with gaps, enabling more accurate spectral analysis and detection of astrophysical signals.

Findings

Detects differential rotation in Kepler star KIC 6102338.

Identifies oscillation modes in K2 light curve of EPIC 203354381.

Suppresses spectral artifacts and improves dynamic range.

Abstract

While the Lomb-Scargle periodogram is foundational to astronomy, it has a significant shortcoming: the variance in the estimated power spectrum does not decrease as more data are acquired. Statisticians have a 60-year history of developing variance-suppressing power spectrum estimators, but most are not used in astronomy because they are formulated for time series with uniform observing cadence and without seasonal or daily gaps. Here we demonstrate how to apply the missing-data multitaper power spectrum estimator to spacecraft data with uniform time intervals between observations but missing data during thruster fires or momentum dumps. The F-test for harmonic components may be applied to multitaper power spectrum estimates to identify statistically significant oscillations that would not rise above a white noise-based false alarm probability. Multitapering improves the dynamic range of the power spectrum estimate and suppresses spectral window artifacts. We show that the multitaper - F-test combination applied to Kepler observations of KIC 6102338 detects differential rotation without requiring iterative sinusoid fitting and subtraction. Significant signals reside at harmonics of both fundamental rotation frequencies and suggest an antisolar rotation profile. Next we use the missing-data multitaper power spectrum estimator to identify the oscillation modes responsible for the complex "scallop shell" shape of the K2 light curve of EPIC 203354381. We argue that multitaper power spectrum estimators should be used for all time series with regular observing cadence.