Collaborative Research: AI-Powered Discovery of The Faintest Galaxies: Pushing the Galaxy Formation Frontier

This program will use artificial intelligence (AI) to detect a large sample of the faintest and smallest galaxies in the Universe. With an innovative computer code, this research team will analyze vast datasets obtained by the most advanced astronomical observatories, among them the Rubin telescope. Dwarf galaxies are faint and small, which makes them difficult to detect in astronomical images. With the power of AI, this program will discover a solid statistical sample of elusive distant dwarf galaxies. The investigators supported by this program will create a series of video blogs (vlogs) that explain the process of scientific discovery to everyone, from middle schoolers to general audiences. These videos will be shared on existing YouTube platforms that have thousands of subscribers. The main scientific goal of this program is to use a convolutional neural network image classifier to build an unbiased sample of the faintest dwarfs beyond the Local Group, including isolated dwarf galaxies. This program will also characterize these newly discovered systems with follow-up observations. These discoveries will be put into context with other dwarf galaxies in and beyond the Local Group, which will illuminate many aspects of small-scale galaxy formation. This program will also build a valuable training sample for future searches of dwarf galaxies, maximizing the full scientific potential of upcoming Rubin/LSST observations. The PI of this program, a senior TED fellow, will continue to engage the public with outreach talks and video blogs that explain science concepts to everyone. This research award is partially funded by a generous gift from Charles Simonyi to the NSF Astronomy division. The project includes significant contributions to Vera C. Rubin Observatory’s Legacy Survey of Space and Time. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.