New Zealand Statistical Association 2024 Conference

Matt Edwards

University of Auckland

A novel stacked hybrid autoencoder for imputing data gaps in the Laser Interferometer Space Antenna

This is joint work with Ruiting Mao, Kate Lee

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 number and duration, that we yield an overlap of greater than 99.9% when the gaps do not occur in the merging phase, and greater than 98% 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.