2022ApJ...939...13C

Detecting gravitational waves from a nearby core-collapse supernova would place meaningful constraints on the supernova engine and nuclear equation of state. Here we use convolutional neural network models to identify the core rotational rates, rotation length scales, and the nuclear equation of state (EoS), using the 1824 waveforms from Richers et al. for a 12 solar mass progenitor. A high prediction accuracy for the classifications of the rotation length scales (93%) and the rotational rates (95%) can be achieved using the gravitational-wave signals from -10 to 6 ms core bounce. By including an additional 48 ms signal during the prompt convection phase, we could achieve an accuracy of 96% in the classification of the four main EoS groups. By combining the three models above, we could correctly predict the core rotational rates, rotation length scales, and the EoS at the same time with an accuracy of more than 85%. Finally, applying a transfer-learning method for an additional 74 waveforms from FLASH simulations, we show that our model using Richers' waveforms could successfully predict the rotational rates from Pan's waveforms even for a continuous value with mean absolute errors of 0.32 rad s^–1 only. These results demonstrate the much broader parameter regimes to which our model can be applied to identify core-collapse supernova events through gravitational-wave signals.