Alien hunters get a boost as AI helps identify promising signals from space

Shutterstock“>

An international team of researchers searching for signs of intelligent life in space have used artificial intelligence (AI) to spot eight promising radio signals in data collected at a US observatory.

The results of their research, published in natural astronomy are remarkable. The team hasn’t performed a comprehensive analysis, but the paper suggests the signals exhibit many of the properties we would expect if they were artificially generated. In other words, it’s the kind of signals we could be picking up from an extraterrestrial civilization broadcasting into space.

A cursory examination of the new paper suggests these are indeed promising signals. You’re far more persuasive than perhaps the most famous SETI candidate who yelled “Wow!” Signal, radio emission with characteristics of extraterrestrial origin, collected by an Ohio telescope in 1977.

Realistically, it is most likely that these eight new signals were created by human technology. But the real story here is the effectiveness of the AI ​​and techniques the team is using to unearth rare and interesting signals that were previously hidden in the noise of human-made radio frequency interference like cellphones and GPS.

Astronomers working in the field of SETI (the search for extraterrestrial intelligence) need to filter out interference generated by radio communications here on Earth.

In this case, University of Toronto’s Peter Ma and colleagues unleashed a suite of algorithms on a mountain of data collected by the Green Bank Telescope in West Virginia, USA. The data was collected as part of a SETI initiative called Breakthrough Listen, founded in 2015 by investor Yuri Milner and his wife Julia.

Here are the properties astronomers look for in signals that could be artificially generated: First, they are narrow-band, meaning radio transmission is limited to just a few frequency channels. They also disappear when the telescope is moved in a different direction across the sky, and they exhibit “Doppler drift,” where the signal’s frequency changes in a predictable way over time. We would expect the Doppler to drift as both the transmitter – say on a distant planet – and the receiver are moving on Earth.

Buried in the noise

The first candidate signal from the Breakthrough Listen project called BLC1 was first announced in 2020. However, it was later traced to transmissions related to cheap electronic devices on this planet. However, the application of AI techniques to the Breakthrough Listen observing program is a potential game-changer for the field. Even seasoned SETI researchers are beginning to think we may be on the cusp of a significant scientific breakthrough.

This could explain renewed interest from groups around the world planning SETI’s success. For example, a SETI post-detection hub has been set up at the University of St Andrews in Scotland. This will explore how humans should react when we discover that we are not alone in the universe.

The SETI Standing Committee of the International Academy of Astronautics (IAA) oversees the SETI post-detection protocols, which describe what steps scientists should take when they spot a real signal. The ILO has decided to update the text of the minutes later this year.

However, the new study highlights an issue with previous signals of interest. When the team took another look at the stars associated with the eight narrowband transmissions, they couldn’t see the signals anymore.

It would not be surprising if many, and perhaps the vast majority, of genuine SETI signals were isolated events. After all, what are the chances that we will repeatedly point our telescopes in the right direction, at the right time and with the right frequency?

Missing ingredients

As I argued here a few years ago, SETI surveys would benefit greatly from the use of multiple radio telescopes operating in a manner known as a classical interferometer network.

These telescope arrays (groups of several antennas observing together) generate huge amounts of data. With AI on board, the challenge may be more manageable than previously thought.

Breakthrough Listen is already using telescope arrays such as MeerKAT in South Africa for SETI searches. In Europe, researchers have been experimenting with arrays spanning the globe.

This European approach would help us isolate signals from man-made interference, give us multiple independent detections of single events, and allow us to locate signals to individual stars and possibly orbiting planets.

Future projects include the Square Kilometer Array, an international project to build the world’s two largest telescope arrays, which will be based in Australia and South Africa. Another upcoming project is the Next Generation VLA (ngVLA), a series of interconnected telescope facilities that will be spread across the United States. These radio telescope arrays will be even more sensitive than current instruments.

I believe – and indeed hope – that intelligent beings are out there somewhere, waiting to be discovered. The AI ​​revolution could be the missing ingredient that previous efforts have lacked. AI algorithms in particular will eventually evolve into powerful tools that no longer suffer from human bias.

Lord Martin Rees, Chair of the Advisory Board to Breakthrough Listen and Astronomer Royal, has suggested that if we do find aliens, they are likely to be intelligent machines working in deep space, regardless of the biological constraints imposed on humans .

If we ever find a real signal, it could simply be mediated by machines on Earth and in space.

This article was republished by The Conversation under a Creative Commons license. Read the original article.