Astronomers used machine learning to mine SA’s MeerKAT telescope data…

Machine Learning

New telescopes with unprecedented sensitivity and resolution are being announced around the world. Among them are the Giant Magellan Telescope under construction in Chile and the James Webb Space Telescope located 1.5 million km away from him in space.

This means there is a wealth of data available to scientists. Raw data from his one observation of the MeerKAT radio telescope in the Northern Cape Province of South Africa can measure 1 terabyte. This is enough to fill up the hard drive of a laptop computer.

MeerKAT is an array of 64 large antenna dishes. It uses radio signals from space to study the evolution of the universe and everything it contains, including galaxies. Each dish is said to generate as much data as a DVD in one second.

Machine learning can help astronomers process this data faster and more accurately than manually examining it.

Perhaps surprisingly, despite our increasing reliance on computers, until recently rare and new discoveries in astrophysical phenomena relied entirely on human inspection of data.

Machine learning is basically a set of algorithms designed to automatically learn patterns and models from data. We astronomers don’t know what we’re trying to find, so we also design algorithms to look for anomalies that don’t fit known parameters or “labels.”

This approach allowed my colleagues and I to find previously overlooked objects in the MeerKAT data. It is about 7 billion light years away from Earth. A light year is a measure of the distance light travels in her one year. From what we know so far about this object, it has many components of what is known as the Odd Radio Circle (ORC).

Odd radio circles can be identified by their strange ring-like structure. Only a handful of these circles have been detected since their initial discovery in 2019, so they are still largely unknown.

A new paper outlines the function of a potential ORC named Sauron (a steep, uneven ring of non-thermal radiation). Sauron is, to our knowledge, the first scientific discovery made on his MeerKAT data using machine learning. Several other discoveries were made with the help of machine learning in astronomy.

Not only is discovering something new incredibly exciting, new discoveries are important because they challenge our understanding of the universe. may be consistent with our theory. Or maybe we need to change the way we see the universe. New discoveries of unusual astrophysical objects help advance science.

Anomaly identification

Found Sauron in the data of the MeerKAT Galaxy Cluster Legacy Survey.

The survey is an observational program conducted at the MeerKAT telescope in South Africa, the predecessor of the Square Kilometer Array. The array is a global project to build the world’s largest and most sensitive radio telescopes in South Africa and Australia within the next decade.

This survey was conducted between June 2018 and June 2019. We aimed at about 115 galaxy clusters, each consisting of hundreds or thousands of galaxies.

You need a lot of data to sift through and this is where machine learning comes in.

We developed and used a coding framework called Astronomary to classify our data. Astronomers ranked the unknown objects according to an anomaly scoring system. A team of humans then manually evaluated the 200 anomalies of most interest. We’ve tapped into our vast collective expertise to make sense of the data.

It was in this part of the process that we identified Sauron. Instead of examining 6,000 individual images, he only had to examine the first 60 that astronomy flagged as anomalous to find Sauron.

But questions remain. What did you find, exactly?

Is Sauron an ORC?

We know very little about ORC. These bright explosion-like emissions are now thought to be the remnants of a gigantic explosion in the host galaxy.

The name Sauron captures the basics of object composition. “Steep” refers to the slope of its spectrum, indicating that the “source” (or object) fades very quickly at higher radio frequencies. “Ring” refers to the shape. Also, “non-thermal radiation” refers to a type of radiation, suggesting that there must be particles that accelerate in strong magnetic fields. Sauron is at least 1.2 million light-years across, about 20 times the size of the Milky Way.

But Sauron has not ticked all the appropriate boxes for us to say that it is definitely an ORC. No evidence of radio emission of wavelength and frequency was found.

Although Sauron has much in common with the first discovered ORC, Odd Radio Circle1, but it is different. Its strange shape and strangely behaving magnetic field do not mesh well with the main structure.

One of the most exciting possibilities is that Sauron is the remnant of an explosive merger of two supermassive black holes. These are incredibly dense objects in the centers of galaxies like the Milky Way, which can cause massive explosions when galaxies collide.

more coming

Further investigation is required to unravel the mystery.

Machine learning, on the other hand, is becoming an essential tool for finding stranger objects by classifying vast datasets from telescopes. With this tool, we can expect to reveal more of what the universe hides.

Michelle Lockner University of the Western Cape Senior Lecturer in Astronomy

This article is reprinted from The Conversation under a Creative Commons license. Read the original article here.

AI Masterclass: Moneyweb has partnered with the Institute for Technology Strategy and Innovation and the North-West University Business School to offer groundbreaking new artificial intelligence courses. All Insider Gold subscribers receive a 10% discount on the 4-day virtual course. Click here for more information.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *