Communications of the ACM
Machine Learning Helps Discover the Most Luminous Supernova in History
Machine-learning technology developed by researchers at Los Alamos National Laboratory played a key role in the discovery of supernova ASASSN-15lh.
Credit: Jin Ma/Beijing Planetarium
Los Alamos National Laboratory (LANL) researchers developed machine-learning technology that played a key role in the discovery of supernova ASASSN-15lh, an exceptionally powerful explosion that was twice as bright as the previous record-holding supernova.
"We developed an automated software system based on machine-learning algorithms to reliably separate real transients from bogus detections," says LANL's Przemek Wozniak.
The researchers say the technology will soon enable scientists to find 10 or even 100 times more supernovae, and to explore rare cases in greater detail.
In addition, LANL researchers are developing high-fidelity computer simulations of shock waves and radiation generated in supernovae explosions. "By comparing our models with measurements collected during the onset of a supernova, we will learn about the progenitors of these violent events, the end stages of stellar evolution leading up to the explosion, and the explosion mechanism itself," says LANL researcher Chris Fryer.
The next generation of massive sky monitoring surveys could deliver a steady stream of high-impact discoveries. For example, the Large Synoptic Survey Telescope, expected to launch in 2022, will collect 100 petabytes of imaging data, and the Zwicky Transient Facility, planned to begin operations in 2017, is designed to routinely catch supernovae in the act of exploding.
From Los Alamos National Laboratory News
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found