Title: Invisible Cities: Imagining the next era of AI-enabled fundamental physics research
Abstract: Some of the most exciting fundamental physics discoveries in recent years emerged thanks to large-scale experimental collaborations that radically differed from conventional scientific practices a century ago. The recent success of large-scale AI models trained on highly diverse data sources raises the question: could our scientific conventions yet again be restricting our access to major discoveries in physics? In this talk, I propose that broadening our analyses across datasets, detectors, and even scientific disciplines could be critical to finally answering the grand mysteries of our Universe that have thus far eluded our usual strategies. As we pursue this vision, we will need to consider several distinctive qualities of fundamental physics data that remain under-explored in mainstream AI research, and aim to understand to what extent these features might require specialized treatment from a machine learning perspective.
Bio: Mariel Pettee is an assistant professor of Physics and the Bernice Durand Faculty Fellow at the University of Wisconsin—Madison. Her research involves developing ML methods for particle physics and astrophysics applications as well as building scientific foundation models, with a particular focus on representation learning in multimodal and multidisciplinary scientific data. Previously, she was a Chamberlain Postdoctoral Fellow at Lawrence Berkeley National Laboratory and received her PhD in Physics from Yale University.
For help, please contact Webmaster.