From streaming, repeated, noisy, and distorted images of the sky, time-domain astronomers are tasked with extracting novel science as quickly as possible with limited and imperfect information. Employing algorithms developed in other fields, we have has already reached important milestones demonstrating the speed and efficacy of using ML in data and inference workflows. Now we look to innovations in learning architectures and computational approaches that are purpose-built alongside the specific domain questions. I will describe such efforts—developed in the search for Planet 9, new classes of variable sources, and for data-driven emulators—and discuss on-going efforts to imbue physical understanding into the learning process itself.
Josh Bloom an astronomy professor at the University of California, Berkeley, where he teaches high-energy astrophysics, Python bootcamps, and a graduate-level class on Python for data-driven science. He has published more than 250 refereed articles, largely on time-domain transients events and telescope/insight automation. Expressed in his research is output of a collaborative effort between talented astronomers, statisticians, and computer scientists (ranging from students to peers) at the nexus of physics, scalable computation, and machine learning. His book on gamma-ray bursts was published in 2011, as part of the "Frontiers in Physics" series by Princeton University Press. He has been awarded the Pierce Prize from the American Astronomical Society, and he is a former Sloan Fellow, Junior Fellow at the Harvard Society, and Hertz Foundation Fellow. He holds a PhD from Caltech and degrees from Harvard and Cambridge University. Recently, he has working as co-PI of the Moore-Sloan Data Science Initiative at UC Berkeley and an elected member of the management oversight body of the Large Synoptic Survey Telescope (LSST).