Dr. Kiri Wagstaff
Jet Propulsion Laboratory, National Aeronautics and Space Administration, USA
Machine Learning for Discovery in Radio and Optical Astronomy Investigations
Abstract: Machine learning provides the ability to quickly sift through large data sets to identify observations of known scientific interest and highlight unexpected observations that could lead to new discoveries. I will describe two astronomy projects that leverage machine learning to achieve these goals. The V-FASTR system was designed to enable real-time detection and classification of transient radio pulses in data from the VLBA. V-FASTR also seeks to enable potential discoveries of new radio sources, such as pulsars, star forming regions, and others we haven’t yet categorized. Machine learning is used to filter out spurious detections and reduce the human effort needed to review the detections that arrive each day. Annotations made by reviewers are used to re-train the machine learning classifier each night, enabling continual improvement in classifier performance and in human time saved. Second, we have developed a processing pipeline for galaxy observations from the Dark Energy Survey to identify outliers and generate explanations to help determine whether they (1) indicate an upstream data collection or processing issue or (2) are of scientific interest. Both systems aim to accelerate the process of scientific discovery by directing human attention to where it is most needed.
Leave a Comment
Last Updated: 22nd July 2020 by Simon Purser
2020-07-29, 16:00: Dr. Kiri Wagstaff (NASA JPL)
Dr. Kiri Wagstaff
Jet Propulsion Laboratory, National Aeronautics and Space Administration, USA
Machine Learning for Discovery in Radio and Optical Astronomy Investigations
Abstract: Machine learning provides the ability to quickly sift through large data sets to identify observations of known scientific interest and highlight unexpected observations that could lead to new discoveries. I will describe two astronomy projects that leverage machine learning to achieve these goals. The V-FASTR system was designed to enable real-time detection and classification of transient radio pulses in data from the VLBA. V-FASTR also seeks to enable potential discoveries of new radio sources, such as pulsars, star forming regions, and others we haven’t yet categorized. Machine learning is used to filter out spurious detections and reduce the human effort needed to review the detections that arrive each day. Annotations made by reviewers are used to re-train the machine learning classifier each night, enabling continual improvement in classifier performance and in human time saved. Second, we have developed a processing pipeline for galaxy observations from the Dark Energy Survey to identify outliers and generate explanations to help determine whether they (1) indicate an upstream data collection or processing issue or (2) are of scientific interest. Both systems aim to accelerate the process of scientific discovery by directing human attention to where it is most needed.
Category: Astronomy and Astrophysics, Astronomy and Astrophysics Section News & Events, Future Seminars, Seminars
#BooksofDIAS: Principles of Continuum Mechanics by Zdeněk Martinec (2019) This book addresses the basic concepts of continuum mechanics, that is, the classical field theory of deformable bodies. More: springer.com/gp/book/978303… #DBF2020 #DIASdiscovers
#BooksofDIAS: The MacEgan Legal Treatise (2020) edited by Fergus Kelly This Treatise is of special importance as it provides a professional lawyer’s account of Irish ‘Brehon’ law in the period after the Anglo-Norman invasion of 1169. See more: shop.dias.ie/product/the-ma… #DBF2020
DIAS School of Theoretical Physics is hiring! -Postdoctoral Scholarship in Theoretical Physics -Schrödinger Fellowship in Theoretical Physics Application closes on 10 January 2021. More details and how to apply is on our website: dias.ie/positions/ #jobfairy #physics
DIAS's bookshop is offering some great discounts today. See more on our website: shop.dias.ie #DIASdiscovers #BlackFriday #books #BlackFriday2020
Job Opportunity! DIAS is recruiting for a Senior IT Administrator/Systems Administrator. It is an initial 5 year fixed term contract, with the possibility of a permanent appointment. Closing Date 11 December linkedin.com/jobs/view/seni… #DIASdiscovers #jobfairy #sysadmin #itadmin
Congratulations @TomRayDIAS! A fantastic career to date with more exciting projects on the horizon 👏 twitter.com/DIASAstronomy/…
Welcome to the Research Leaders appointed to DIAS's Council and School Governing Boards. Their individual track records as leaders in their respective fields, will be a great source of insight and inspiration for the wider DIAS community. ▶️ dias.ie/2020/11/23/res… #DIASdiscovers
Glad you enjoyed! twitter.com/krjonsdottir/s…
Tonight! Some tickets still available for @dias_geophysics Statutory public lecture MARSQUAKES! presented by Dr John Clinton of @ETH . Online starting at 16:30pm. #DIASdiscovers eventbrite.ie/e/128258411361
@TurloughDownes @SimonHarrisTD @IrishResearch Congratulations!
..., be appointed Director of the School of Theoretical Physics”, which was seconded by Professor A. J. McConnell and carried unanimously. (4/4) Read more: dias.ie/2010/09/15/stp…
The 21 November, will mark the 80th Anniversary of the first meeting of the Governing Board of the School of Theoretical Physics. The first item on the agenda was a proposal by the Chairman of the Board, Dr. Conway, “that Professor Erwin Schrödinger, (3/4)
During the lunch De Valera outlined his plan for an Institute for Advanced Studies embracing a School of Celtic Learning, a School of Theoretical Physics, and a School of Medical Research, with possible additional sections to be added on later. (2/4)
#OTD in 1903 long serving @StpDias Board member Professor Albert Joseph McConnell was born. Coincidently also #OTD in 1938 McConnell attended a luncheon hosted by then Taoiseach Eamon DeValera in @LeinsterHouse with Erwin Schrödinger (1/4) *picture from 1942