A novel Pytorch based library for time-frequency analysis and preprocessing of gravitational wave data.
It includes a channel selection algorithm that makes use of time-frequency domain representation of the data, namely the QTransform, to evaluate correlations among the main and auxiliary channels as a measure of temporally coincident spikes in the energetic content of the signals above a critical threshold.
To support the channel selection algorithm, it includes pytorch implementations of the relevant preprocessing steps consisting of data resampling, whitening, spectrogram generation, image cropping, and loading into a custom PyTorch dataloader.
Release Notes
The final release of the module is available at https://github.com/interTwin-eu/DT-Virgo-notebooks/tree/main/Final_Release/ANNALISA. The module is implemented as an itwinai plugin, and is installable as pip install itwinai-virgo
Future Plans
The ultimate goal is to make the library an official tool of Detector Characterization within the Virgo and Einstein Telescope Collaboration.
