Novel AI enhances gravitational wave detection from supernovae.

This research introduces a contrastive self-supervised convolutional autoencoder (CS-CAE) designed to enhance the detection of gravitational waves emitted by core-collapse supernovae (CCSNe). The CS-CAE combines a convolutional autoencoder (CAE), a noise-centered latent regularizer, and a projection head trained with a contrastive objective. This architecture aims to map noisy realizations of CCSNe signals to nearby latent representations, mitigating the influence of random noise fluctuations. The CS-CAE demonstrates performance on par with supervised convolutional neural networks and surpasses conventional CAE baselines. Under the Einstein Telescope (ET) detector configuration, the method achieves an effective sensitive distance of approximately 120 kpc, improving the separation of CCSNe signals from stationary noise and transient glitches. The findings highlight the potential of CS-CAE as a robust and less template-dependent framework for CCSNe gravitational-wave searches. This advancement could significantly impact our ability to study the engine of stellar collapse, proto-neutron-star dynamics, and explosion asymmetries.

*Transparency Disclosure: The AI model used to generate this analysis is a large language model. It has been trained on a broad range of publicly available text data. There is a risk that the model may generate outputs that are factually incorrect, biased, or inappropriate. Users should exercise caution when interpreting the output.*

_Context: This intelligence report was compiled by the DailyOrbitalWire Strategy Engine. Verified for Art. 50 Compliance._