Keming Zhang

I’m an Eric and Wendy Schmidt AI in Science Postdoc Fellow at the University of California, San Diego. I obtained my PhD in Astrophysics from the University of California, Berkeley in 2023, and BA in Astrophysics from Columbia University in 2018.

My research focuses on the detection of extrasolar planets via the gravitational microlensing techinique, utilizing a combination of computational, theoretical, and observational approaches. My observational work with the Keck Observatories has led to the discovery of an Earth-sized exoplanet orbiting a White Dwarf at a separation of 2.1 au, “suggesting a future in which our planet outlives its star” (New York Times). My computational and theoretical work has led to the discovery of a unified framework for microlensing degeneracies, and subsequently universal analytic solutions to the binary-lens equation.

I extensively utilize and develop Machine Learning and Simulation-Based Inference techiniques in my research, in order to enable the massively scalable inference required by modern-day astronomical survey experiments. My work on cyclic-permutation invariant networks demonstrate the advantages of incoporating domain-specific inductive biases for physical learning tasks. My open-source software project nbi integrates importance sampling with Neural Posterior Estimation to enable asymptotically exact inference, and facilitates off-the-shelf applications to a wide range of astronomical tasks, such as stellar spectroscopy.

I have also been an avid astrophotographer since childhood. Check out my portfolio.