Artificial intelligence classifies supernova explosions with unprecedented accuracy

December 17, 2020

Cambridge, MA (December 17, 2020)--Artificial intelligence is classifying real supernova explosions without the traditional use of spectra, thanks to a team of astronomers at the Center for Astrophysics | Harvard & Smithsonian. The complete data sets and resulting classifications are publicly available for open use.

By training a machine learning model to categorize supernovae based on their visible characteristics, the astronomers were able to classify real data from the Pan-STARRS1 Medium Deep Survey for 2,315 supernovae with an accuracy rate of 82-percent without the use of spectra.

The astronomers developed a software program that classifies different types of supernovae based on their light curves, or how their brightness changes over time. "We have approximately 2,500 supernovae with light curves from the Pan-STARRS1 Medium Deep Survey, and of those, 500 supernovae with spectra that can be used for classification," said Griffin Hosseinzadeh, a postdoctoral researcher at the CfA and lead author on the first of two papers published in The Astrophysical Journal. "We trained the classifier using those 500 supernovae to classify the remaining supernovae where we were not able to observe the spectrum."

Edo Berger, an astronomer at the CfA explained that by asking the artificial intelligence to answer specific questions, the results become increasingly more accurate. "The machine learning looks for a correlation with the original 500 spectroscopic labels. We ask it to compare the supernovae in different categories: color, rate of evolution, or brightness. By feeding it real existing knowledge, it leads to the highest accuracy, between 80- and 90-percent."

Although this is not the first machine learning project for supernovae classification, it is the first time that astronomers have had access to a real data set large enough to train an artificial intelligence-based supernovae classifier, making it possible to create machine learning algorithms without the use of simulations.

"If you make a simulated light curve, it means you are making an assumption about what supernovae will look like, and your classifier will then learn those assumptions as well," said Hosseinzadeh. "Nature will always throw some additional complications in that you did not account for, meaning that your classifier will not do as well on real data as it did on simulated data. Because we used real data to train our classifiers, it means our measured accuracy is probably more representative of how our classifiers will perform on other surveys." As the classifier categorizes the supernovae, said Berger, "We will be able to study them both in retrospect and in real-time to pick out the most interesting events for detailed follow up. We will use the algorithm to help us pick out the needles and also to look at the haystack."

The project has implications not only for archival data, but also for data that will be collected by future telescopes. The Vera C. Rubin Observatory is expected to go online in 2023, and will lead to the discovery of millions of new supernovae each year. This presents both opportunities and challenges for astrophysicists, where limited telescope time leads to limited spectral classifications.

"When the Rubin Observatory goes online it will increase our discovery rate of supernovae by 100-fold, but our spectroscopic resources will not increase," said Ashley Villar, a Simons Junior Fellow at Columbia University and lead author on the second of the two papers, adding that while roughly 10,000 supernovae are currently discovered each year, scientists only take spectra of about 10-percent of those objects. "If this holds true, it means that only 0.1-percent of supernovae discovered by the Rubin Observatory each year will get a spectroscopic label. The remaining 99.9-percent of data will be unusable without methods like ours."

Unlike past efforts, where data sets and classifications have been available to only a limited number of astronomers, the data sets from the new machine learning algorithm will be made publicly available. The astronomers have created easy-to-use, accessible software, and also released all of the data from Pan-STARRS1 Medium Deep Survey along with the new classifications for use in other projects. Hosseinzadeh said, "It was really important to us that these projects be useful for the entire supernova community, not just for our group. There are so many projects that can be done with these data that we could never do them all ourselves." Berger added, "These projects are open data for open science."
-end-
This project was funded in part by a grant from the National Science Foundation (NSF) and the Harvard Data Science Initiative (HDSI).

References:

SuperRAENN: A semi-supervised supernova photometric classification pipeline trained on Pan-STARRS1 Medium Deep Survey supernovae, A. Villar et al, The Astrophysical Journal, 2020 December 17
[doi: 10.3847/1538-4357/abc6fd, preprint: https://arxiv.org/pdf/2008.04921.pdf]

Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot by G. Hosseinzadeh et al, The Astrophysical Journal, 2020 December 17,
[doi: 10.3847/1538-4357/abc42b, preprint: https://arxiv.org/pdf/2008.04912.pdf]

About Center for Astrophysics | Harvard & Smithsonian

Headquartered in Cambridge, MA, the Center for Astrophysics (CfA) | Harvard & Smithsonian is a collaboration between the Smithsonian Astrophysical Observatory and the Harvard College Observatory. CfA scientists study the origin, evolution and ultimate fate of the universe.

Harvard-Smithsonian Center for Astrophysics

Related Supernovae Articles from Brightsurf:

FSU-led research team discovers unique supernova explosion
A 7-member international research team led by Florida State University Assistant Professor of Physics Eric Hsiao discovered a supernova that could help uncover the origins of the group of supernovae this star belongs to.

Discovery lays blame on supernova for extinction event nearly 360 million years ago
Between a decline in biodiversity and a series of extinction events, the Late Devonian period was not the most hospitable time on Earth.

New insights about the brightest explosions in the Universe
Swedish and Japanese researchers have, after ten years, found an explanation to the peculiar emission lines seen in one of the brightest supernovae ever observed -- SN 2006gy.

New study sheds light on conditions that trigger supernovae explosions
For the first time, researchers were able to demonstrate the process of detonation formation using both experiments and numerical simulations carried out on supercomputers.

Scientists observe year-long plateaus in decline of type Ia supernova light curves
A team of scientists, including a researcher from Queen's University Belfast, have discovered that the fading of infrared light following Type Ia supernovae explosions can be interrupted, with brightness staying the same for up to a year.

Hubble sets sights on an explosive galaxy
When massive stars die at the end of their short lives, they light up the cosmos with bright, explosive bursts of light and material known as supernovae.

Subaru Telescope captures 1800 exploding stars
The Subaru Telescope has captured images of more than 1800 exploding stars in the Universe, some located 8 billion light years from Earth.

Researchers wonder if ancient supernovae prompted human ancestors to walk upright
Supernovae bombarded Earth with cosmic energy starting as many as 8 million years ago, with a peak some 2.6 million years ago, initiating an avalanche of electrons in the lower atmosphere and setting off a chain of events that feasibly ended with bipedal hominins.

Stars exploding as supernovae lose their mass to companion stars during their lives
Stars over eight times more massive than the sun end their lives in supernovae explosions.

Zwicky Transient Facility spots a bumper crop of supernovae, black holes and more
The Zwicky Transient Facility (ZTF), an automated sky survey project based at Caltech's Palomar Observatory near San Diego, California, has produced its first bounty of new results.

Read More: Supernovae News and Supernovae Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.