Dmitry Duev is a Research Scientist at the Astronomy Department of the California Institute of Technology.
Dmitry's research interests cover a wide range of topics across astroinformatics, machine learning, and radio and optical astronomy. He received his Ph.D. degree in Astronomy from the Lomonosov Moscow State University, Russia and worked at the Joint Institute for VLBI ERIC in Dwingeloo, The Netherlands before joining Caltech in 2015.
Machine Learning for the Zwicky Transient Facility
Astronomy, as many other branches of science, has been experiencing an explosive increase in the data volumes, doubling every two years or so. At the forefront of this revolution, the Zwicky Transient Facility (ZTF) – a robotic optical sky survey currently in operation at the Palomar Observatory in Southern California – performs accurate measurements of over a billion of astronomical objects and registers ~millions of transient events (such as, for example, supernova explosions, brightness changes in variable stars, or asteroid detections -- distributed to the world in real time via alert streams) in the dynamic sky every (clear) night. Machine and deep learning play an essential role in making sense of these vast quantities of data. In my talk, I will discuss the wide range of applications of machine learning in ZTF, including the astrophysical object classification, identification of near-Earth objects, detection and localization of comets, and cataloging/studying the source variability.