Deep learning in radio astronomy

Title: Deep learning in radio astronomy
Lecturer: Vesna Lukic, postdoc, Vrije Universiteit Brussel, Belgium

Abstract

Machine learning techniques have proven to be increasingly useful in astronomical applications over the last few years, for example in image classification and time series analysis. A topic of current interest is the classification of radio galaxy morphologies, as it gives us insight into the nature of the Active Galactic Nuclei and structure formation. Future surveys, for example with the Square Kilometre Array (SKA), will detect many million sources and will require the use of automated techniques.

Convolutional neural networks are a machine learning technique that have been very successful in image classification, due to their ability to capture high-dimensional features in the data. A drawback of the technique is the use of the pooling operation, which results in information losses and does not preserve the relative position of features in the image. Capsule networks however preserve this information with the use of dynamic routing.

We explore a couple of convolutional neural network architectures against variations of Capsule network setups and evaluate their performance in replicating the classifications of radio galaxies detected by the Low Frequency Array (LOFAR). Finally, we also show how it is possible to use convolutional neural networks to find sources in radio surveys.

About Vesna Lukic

I hold degrees in Engineering and Physics and have worked in the Bioinformatics field after completing my masters. Last year I completed my PhD on the use of deep learning methods applied to radio astronomy data at the University of Hamburg. I am currently a Postdoc at the VUB in Brussels working on energy reconstruction techniques applied to the detection of neutrinos with particle-induced cascades in ice using radar.

Image: Spectacular jets powered by the gravitational energy of a super massive black hole in the core of the elliptical galaxy Hercules A illustrate the combined imaging power of two of astronomy's cutting-edge tools, the Hubble Space Telescope's Wide Field Camera 3, and the recently upgraded Karl G. Jansky Very Large Array (VLA) radio telescope in New Mexico. Credit: NASA, ESA, S. Baum and C. O'Dea (RIT), R. Perley and W. Cotton (NRAO/AUI/NSF), and the Hubble Heritage Team (STScI/AURA)