Main Colloquium
Professor Caroline Heneka	SCHEDULED

University of Heidelberg

The era of radio astronomy is rapidly transforming as next-generation instruments, in particular the Square Kilometre Array (SKA), begin to map vast portions of the observable Universe. These surveys generate enormous and complex datasets, from millions of galaxies across cosmic time to mappings of the intergalactic medium and large-scale structure via the 21cm background during the Epoch of Reionization. Modern AI and machine learning methods are becoming essential for extracting scientific insight from these data. In this talk, I will highlight how flexible, data-driven approaches enable robust scientific analyses across the full workflow from simulations and observational modeling to inference, and show how they help to gain insights on galaxy evolution, the properties of the intergalactic medium, and fundamental physics, while accelerating discovery across large radio surveys.