One of the major challenges in the study of explosive transients is their detection and characterisation using multiple messengers, which often represent different physical regimes and temporal scales. I describe a novel data-driven framework, which is intended to enhance the discovery potential of current and upcoming experiments. Particularly, it is intended for near- and real-time analyses, which are essential for effective follow-up across instruments. The approach is based on anomaly detection techniques, coupling deep learning, time-series analysis, and Bayesian inference. I demonstrate applications focused on the study of gamma-ray bursts, supernovae, primordial black holes, and active galactic nuclei. These involve the combination of multiwavelength data, ranging from optical to gamma-rays, as well as neutrinos.
This is a VIDEO COLLOQUIUM!
Connection details at https://desy.zoom.us/j/99616528733
Meeting ID: 996 1652 8733
Meeting Password: 733220