In the Media
Lecture at the Royal Society of Astronomy
“Real-time classification of explosive transients using deep recurrent neural networks”
RAS Specialist Discussion, 8th March 2019 by Daniel Muthukrishna (University of Cambridge).
By Michael Foley – June 7, 2019.
Presentation to LSST data science
Mt Stromlo Observatory – Supernova Sightings
Dan is currently developing software designed to make the classification of supernovae faster and more accurate. If you are interested in joining the Citizen Science Project: Supernova Sightings, sign up at https://www.zooniverse.org/projects/skymap/supernova-sighting
Posted by Mt Stromlo Observatory on Tuesday, September 19, 2017
Gemini Focus Internships
http://www.gemini.edu/images/pio/newsletters/pdf/gf_0417.pdf. Gemini Focus. Page 27.
ANU astronomers in search for Planet Nine during “Stargazing Live”
- et al. (many more media announcements about the ANU SkyMapper and Zooniverse led project)
DASH cuts supernova classification times
Congratulations to the AGUSS recipients for 2016/17
CAASTRO student’s DASH will speed up supernova classification
CAASTRO student Daniel Muthukrishna has improved the speed at which supernova can be classified by building a program that works in the same way as the human brain – and has won an award for this project.
Daniel, a software engineering student at the University of Queensland, has received the 2016 Student Thesis prize given by the Queensland chapter of the Institute of Electrical and Electronics Engineers (IEEE).
For his thesis, Daniel developed new software for a CAASTRO-supported project, the OzDES redshift survey. Called DASH, the software greatly speeds up the process of classifying supernova taken from OzDES observations.
The code uses Deep Learning, a machine learning technique where the program is trained to look for patterns in the supernova templates and use these to identify the new spectra, but without these patterns being identified beforehand. The machine can learn for itself, in the same manner as a human brain can.
The code has already been used to analyse spectra taken by the AAT and returns the same results as the standard human-intensive process, but in a fraction of the time. Although the code has been developed to help with the OzDES analysis, it is very generic in the analysis approach, and would be usable by any spectroscopic supernova survey.
Daniel’s thesis also won the GBST Prize for “Best software project prize” at the UQ Innovation Showcase event in November. He is currently on a ten-week research placement at the Gemini South Observatory in Chile, as one of the two Australian Gemini Undergraduate Summer Students for 2016.
GBST Best Software Project
GBST were again proud to sponsor the Best Software Project Prize at the UQ ITEE Innovation Showcase this month, where over 60 UQ students across multiple IT and Electrical Engineering disciplines demonstrated their innovative projects. A big congratulations to the winner, Daniel Muthukrishna, whose project “DASH: Deep Learning for Special Classification of Astronomical Objects”, caught the eye of the judges due to its application of complex machine learning and the fact it was already being used in industry. Well done Daniel!
Royal Society of Chemistry
Daniel Muthukrishna’s submission was one of the Top 10 out of 22000 entrants in the Royal Society of Chemistry’s global competition to explain the Mpemba Effect: why hotter water freezes faster than colder water.