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
If you haven't seen it yet check out this amazing video created by @hogg82 of @dias_geophysics . Simply stunning 🤩 twitter.com/hogg82/status/…
This #WorldBookDay we couldn't pick just one DIAS book to tell you about. And so we decided to highlight our wonderful DIAS Bookshop managed by our School of Celtic Studies. Learn more about the titles available here: shop.dias.ie/product-catego… #DIASdiscovers #WorldBookDay2021
Thanks @siliconrepublic for helping to share the findings siliconrepublic.com/innovation/iri…
DIAS scientists’ part of research team to record first ever detailed description of a volcanic eruption from Sierra Negra. Read more: dias.ie/2021/03/04/dia… #DIASdiscovers @dias_geophysics #volcano #Galapagos Image courtesy of @AndyFBell
Meet the Judges of our "Reach for the Stars" Astrophotography competition! Brenda Fitzsimons is photo editor of the @IrishTimes. To learn more about the competition and submit an entry see dias.ie/reachforthesta… #DIASdiscovers #astrophotography
Nice work 👏 twitter.com/dias_geophysic…
Following on from our post, highlighting inspiring #WomeninResearch and encouraging #MondayMotiviation to explore these subjects. @ChantalKobel presents Celticist, Nessa Ní Shéaghdha and her contributions to the discipline youtu.be/LGPLltjTBKw #DIASdiscovers
We have entered the last month to capture that amazing photo of the sky and win our Astrophotography competition. We are accepting photographs taken between 01 January 2020 and 31 March 2021. You can submit an entry up to Friday 02nd April 2021. More: dias.ie/reachforthesta…
Meet the Judges of our "Reach for the Stars" Astrophotography competition! @petertgallagher is Head of @DIASAstronomy & has spent the past two decades studying the Sun its impacts on the Earth. To learn more and submit an entry see dias.ie/reachforthesta… #DIASdiscovers