A novel stacked hybrid autoencoder for imputing LISA data gaps

Abstract

The Laser Interferometer Space Antenna (LISA) data stream will contain gaps with missing or unusable data due to antenna repointing, orbital corrections, instrument malfunctions, and unknown random processes. We introduce a new deep learning model to impute data gaps in the LISA data stream. The stacked hybrid autoencoder combines a denoising convolutional autoencoder (DCAE) with a bi-directional gated recurrent unit (BiGRU). The DCAE is used to extract relevant features in the corrupted data, while the BiGRU captures the temporal dynamics of the gravitational-wave signals. We show for a massive black hole binary signal, corrupted by data gaps of various numbers and duration, that we yield an overlap of greater than 99.97% when the gaps do not occur in the merging phase and greater than 99% when the gaps do occur in the merging phase. However, if data gaps occur during merger time, we show that we get biased astrophysical parameter estimates, highlighting the need for "protected periods," where antenna repointing does not occur during the predicted merger time.

References in corpus (10)

• Laser Interferometer Space Antenna
• Gravitational-wave parameter estimation with gaps in LISA: a Bayesian data augmentation method
• GPU-accelerated massive black hole binary parameter estimation with LISA
• Eryn : A multi-purpose sampler for Bayesian inference
• Probing white dwarf interiors with LISA: periastron precession in double white dwarfs
• Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data
• Gravitational Wave Signal Extraction Against Non-Stationary Instrumental Noises with Deep Neural Network
• Deep-Learning Classification and Parameter Inference of Rotational Core-Collapse Supernovae
• Generative adversarial network for stellar core-collapse gravitational waves
• Calibrating approximate Bayesian credible intervals of gravitational-wave parameters

Cited by in corpus (3)

• Handling Data Gaps for the Next Generation of Gravitational-Wave Observatories
• De-Biasing Structure Function Estimates From Sparse Time Series of the Solar Wind: A Data-Driven Approach
• Accurate and efficient simulation-based inference for massive black-hole binaries with LISA