Publications

We provide a brief, and inevitably incomplete overview of the use of Machine Learning (ML) and other AI methods in astronomy, astrophysics, and cosmology. Astronomy entered the big data era with the … first digital sky surveys in the early 1990s and the resulting Terascale data sets, which required automating of many data processing and analysis tasks, for example the star-galaxy separation, with billions of feature vectors in hundreds of dimensions. The exponential data growth continued, with the rise of synoptic sky surveys and the Time Domain Astronomy, with the resulting Petascale data streams and the need for a real-time processing, classification, and decision making. A broad variety of classification and clustering methods have been applied for these tasks, and this remains a very active area of research. Over the past decade we have seen an exponential growth of the astronomical literature involving a variety of ML/AI applications of an ever increasing complexity and sophistication. ML and AI are now a standard part of the astronomical toolkit. As the data complexity continues to increase, we anticipate further advances leading towards a collaborative human-AI discovery.

Abstract Photometric reverberation mapping can detect the radial extent of the accretion disc (AD) in Active Galactic Nuclei by measuring the time delays between light curves observed in different …rves observed in different continuum bands. Quantifying the constraints on the efficiency and accuracy of the delay measurements is important for recovering the AD size-luminosity relation, and potentially using quasars as standard candles. We have explored the possibility of determining the AD size of quasars using next-generation Big Data surveys. We focus on the Legacy Survey of Space and Time (LSST) at the Vera C. Rubin Observatory, which will observe several thousand quasars with the Deep Drilling Fields and up to 10 million quasars for the main survey in six broadband filter during its 10-year operational lifetime. We have developed extensive simulations that take into account the characteristics of the LSST survey and the intrinsic properties of the quasars. The simulations are used to characterise the light curves from which AD sizes are determined using various algorithms. We find that the time delays can be recovered with an accuracy of 5 and 15% for light curves with a time sampling of 2 and 5 days, respectively. The results depend strongly on the redshift of the source and the relative contribution of the emission lines to the bandpasses. Assuming an optically thick and geometrically thin AD, the recovered time-delay spectrum is consistent with black hole masses derived with 30% uncertainty.