Sign In

Communications of the ACM

ACM TechNews

ML Tools Automatically Classify 1,000 Supernovae

View as: Print Mobile App Share:
The 48-inch Samuel Oschin Telescope at Palomar Observatory where ZTF is housed.

Currently, SNIascore can classify what are known as Type Ia supernovae, or the "standard candles" in the sky.

Credit: Palomar/Caltech

A machine learning algorithm developed by astronomers at the California Institute of Technology (Caltech) autonomously classified 1,000 supernovae using data from the Zwicky Transient Facility (ZTF) sky survey instrument at Caltech's Palomar Observatory.

The SNIascore algorithm hit that milestone 18 months after classifying its first supernova, in April 2021.

The algorithm is intended to help the ZTF team by processing data from the hundreds of thousands of transient events ZTF detects every night.

SNIascore currently has the ability to classify Type Ia supernovae that astronomers use to measure the universe's expansion rate.

The researchers are working to enable the algorithm to classify other types of supernovae as well.

From Caltech News
View Full Article


Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account