Universe is 93 billion light years big in diameter and finding exactly want you want in this huge space is really a painful task. Luckily we have AI.
Scientists have detected some unusual radio signals in galaxy. While searching for extraterrestrial life, researchers at the Search for Extraterrestrial Intelligence (SETI ) have spotted 72 mysterious signals with the help of there artificial intelligence system.
The signals where coming from an alien galaxy which is 3 billion light years from Earth. They have discovered the unusual signals when they were examining 400 terabytes of radio data from a dwarf galaxy.
The FRBs are coming from the only known source that has sent out repeating blast. Researcher called it FRB 121102. Breakthrough Listen observations made in 2017 with the Green Bank Telescope in West Virginia, FRB 121102 emitted 21 bursts. When combined it with the previous observation, now astronomers have found 93 FRBs.
Fast radio bursts are high-energy astrophysical phenomenon of unknown origin. They are like a bright pulses of radio emission, each flare only lasts a few milliseconds and FBR’s are thought to be originated from distant galaxies.
Fast radio bursts remain one of the most head-scratching phenomena in the universe. Only about 30 events have been confirmed since they were discovered over a decade ago.
This new study is published in the The Astrophysical Journal. The project led by the University of California, Berkeley. In this study researchers describes how they used data previously collected from fast radio bursts (FRBs) to train a neural network to find dozens more in already-collected data.
“This work is exciting not just because it helps us understand the dynamic behavior of fast radio bursts in more detail, but also because of the promise it shows for using machine learning to detect signals missed by classical algorithms,” according to Andrew Siemion, director of the Berkeley SETI Research Center and principal investigator of Breakthrough Listen.
For the detection of fast radio bursts (FRB) researchers team developed a powerful machine-learning algorithm. It was firstly created by Gerry Zhang, a PhD student at Berkeley. Zhang’s team used some of the same techniques that internet technology companies use to optimize search results and classify images.
They trained an algorithm known as a convolutional neural network to recognize FRB’s using 2017 dataset of 400tb data, in which another researcher had already identified 21 FRB’s. It was trained to look for the characteristics of the blasts and then try and spot them in the dataset, looking through it far more quickly than a human ever could. In that dataset the algorithm identified a whopping 72 new FRBs, bringing the number recognized from that single source to about 30.
“This work is only the beginning of using these powerful methods to find radio transients,” Gerry Zhang, a doctoral student at UC Berkeley who led the AI development, said in a statement. “We hope our success may inspire other serious endeavors in applying machine learning to radio astronomy.”
“Not all discoveries come from new observations,” says Pete Worden, executive director of the Breakthrough Listen and other Breakthrough Initiatives, “In this case, it was smart, original thinking applied to an existing dataset. It has advanced our knowledge of one of the most tantalizing mysteries in astronomy.”
“In this case, it was smart, original thinking applied to an existing dataset,” Worden added. “It has advanced our knowledge of one of the most tantalizing mysteries in astronomy.”
You can read the study from here.
More in AI :