Ensemble | Finding astrophysical sources using machine learning

Ensemble | Finding astrophysical sources using machine learning

Topic: Finding astrophysical sources that pulse and flash using the largest telescopes in the world and machine learning

Guest Speaker: Prof. Benjamin Stappers

Date: Wednesday 20 November 2019

Time: 12:00 – 13:00 GMT

Location: Peak HQ, 12th Floor, Neo Building, Charlotte Street. Manchester, M1 4ET.


Sign up


Event Description

Ensemble is an artificial intelligence, machine learning and data science event held regularly at Peak in Manchester. Like an ensemble model, the event will allow learning through exposure to a diverse set of experiences. Each month, a top researcher from the fields of computer science, statistics or operational research will be invited to present their work. The audience will be made up of data scientists, software engineers, researchers and company CIOs from tech companies and universities.

This will be a great opportunity to learn and network with fellow professionals and academics in the field.

Talk abstract:

Astrophysical sources of radio emission are very weak and require the largest possible radio telescopes to detect them. The Square Kilometre Array (SKA) will be the largest telescope in the world and is currently being designed ready for deployment to Southern Africa and Australia in the coming decade Two of the key objects for the study with the SKA are pulsars and fast radio bursts (FRBs). The former are characterised by short (nano-second to second) pulses of radio emission which repeat from milliseconds to seconds. They are the most compact objects next to black holes and used for tests of theories of gravity, amongst other things. FRBs are a recently discovered phenomenon, the origin of which is still not understood, but they are characterised by millisecond long bursts of emission that are from sources well beyond our galaxy. Finding these objects is proving ever more difficult with surveys generating millions of candidates. I’ll discuss the science, the telescopes and the machine learning approaches we are taking to find these objects and the challenges that arise.

Speaker Bio:

Ben is a Professor of Astrophysics in the Jodrell Bank Centre for Astrophysics which is in the Department of Physics and Astronomy at the University of Manchester. My primary research interests are radio pulsars, neutron stars and rapid radio transients. My main area of research at the moment is through a European Research Council funded project called MeerTRAP to find pulsars and fast radio bursts using the Square Kilometer Array (SKA) radio telescope pathfinder called MeerKAT. As well as using next generation telescopes I am also involved in the specification of various aspects of the SKA itself which will be the world’s larges telescope. We are currently undertaking the design work for the pulsar and fast transient search capabilities of the SKA.

As well as being interested in the science of radio astronomy and pulsars in particular I am interested in the hardware and software associated with their study. These are big data in many senses of the word and we have been working applying Machine Learning approaches to try and reduce the burden on human involvement in decisions on what are real sources or not.


Sign up

Stay in touch!

Subscribe to our newsletter to find out what's going on at Peak.