Artificial intelligence is looking for the ‘needle of life in a cosmic haystack’

About 540 million years ago, diverse life forms suddenly began to emerge from the muddy ocean floors of planet Earth. This period is known as the “Cambrian Explosion.” These aquatic creatures are our ancient ancestors.
All complex life on Earth evolved from these underwater creatures, and scientists believe that all it took was a slight increase in oxygen levels in the oceans above a certain threshold.
We may now be in the midst of the Cambrian explosion of AI in the past few years, and a series of AI programs with astounding capabilities such as Medjourney, Dole2 and ChatGPT have demonstrated the rapid progress we have made in machine learning.

Artificial intelligence is now used in almost all areas of science to assist researchers with routine classification tasks, according to Science Alert.
It also helps the team of radio astronomers expand the search for extraterrestrial life, and results have been promising so far.
Detecting alien signals using artificial intelligence
As scientists search for evidence of intelligent life outside Earth, scientists have built an artificial intelligence system that outperforms classical algorithms in signal detection tasks, Science Alert reported, citing research in the scientific journal Nature.
The AI is trained to search data from radio telescopes for signals that cannot be generated by normal astrophysical processes.
“When we fed our artificial intelligence a previously studied dataset, we detected eight important signals that the classical algorithm missed. These signals are likely not from extraterrestrial intelligence, and are most likely rare cases of radio interference,” Science Alert quotes the researchers.
However, our findings highlight that AI technologies will certainly play an ongoing role in the search for extraterrestrial intelligence.

Not very smart
“AI algorithms don’t ‘understand’ or ‘think’,” said Science Alert. They excel at recognizing patterns, and they’ve proven extremely useful for tasks like classification, but they don’t have the ability to solve problems. They only do the specific tasks they’ve been trained on. do it.”
So, although the idea of detecting extraterrestrial intelligence sounds like the plot of a sci-fi thriller, both terms are flawed, AI programs are not intelligent, and the search for extraterrestrial intelligence cannot find direct evidence of intelligence.
Instead, radio astronomers look for radio “technology fingerprints.” These hypothesized signals indicate the presence of technology and, by extension, the existence of a society with the ability to harness technology for communication.
For our research, we created an algorithm that uses artificial intelligence methods to classify signals as either radio interference, or a true technical fingerprint filter, and our algorithm works better than we had hoped.
What does an AI algorithm do?
Live Science likens searches for a technological footprint to “looking for a needle in a cosmic haystack.” Radio telescopes produce huge amounts of data, and they have huge amounts of interference from sources such as phones, Wi-Fi and satellites.
Search algorithms must be able to distinguish real technical fingerprints from “false signals”, and to do this quickly our AI classifier fulfills these requirements.

Created by Peter Ma, a student at the University of Toronto and lead author on our paper.
To create a set of training data, Peter Ma, a student at the University of Toronto and lead author on the paper, inserted simulated signals into real data, and then used this data set to train an AI algorithm, called an autoencoder. As the autoencoder processes the data, the AI learns. Identify salient features in the data.
In a second step, these features were fed into an algorithm called a random forest classifier. This classifier creates graphical decision trees to determine if the signal is noteworthy, or just radio interference.

After training our AI algorithm, we fed it more than 150 terabytes of data (480 hours of observation) from the Green Bank Telescope in West Virginia.
The AI identified 20,515 signals, which we then had to manually check. Of these, eight had the characteristics of technological fingerprints and could not be attributed to radio interference.

Eight signs
And Live Science continued: “To try to verify these signals, we went back to the telescope to re-observe all eight important signals, and unfortunately, we were unable to re-discover any of them in our follow-up observations.”
We’ve been through similar situations before. In 2020 we detected a signal that turned out to be radio interference, and while we’ll be monitoring these eight new candidates, the most likely explanation is that they were unusual manifestations of radio interference—that they’re not aliens.

Narrow your search
“Our team recently deployed a powerful signal processor on the Meerkat telescope in South Africa,” Live Science added.
Meerkat uses a technique called interferometry to combine its 64 dishes to act as a single telescope.
This technology is better able to determine where the signal is coming from, which greatly reduces false data from wireless interference.

And the magazine continued: “If astronomers can detect a technological fingerprint that cannot be interpreted as interference, then this strongly indicates that humans are not the only creators of technology within the galaxy, and this will be one of the most profound discoveries imaginable.”
At the same time, if we don’t detect something, it doesn’t necessarily mean that we’re the only “intelligent” species with technological capabilities around. Non-detection could also mean that we haven’t been looking for the right kind of signal, or that our telescopes aren’t sensitive enough yet to detect transmissions. from distant outer planets.

The magazine concluded: “We may need to cross the sensitivity threshold before the discoveries of the Cambrian Explosion can be made. Instead, if we are really on our own, we should reflect on the unique beauty and fragility of life here on Earth.”