Photo: JEFF PACHOUD/AFP/Getty Images
One of the great difficulties that space scientists currently have is being able to sort through all the data that the different instruments that we have at our disposal to observe beyond our planet are accumulating.
In this sense, the reason why we have not yet found signs of technologically advanced extraterrestrial life could simply be because they have been amalgamated among a sea of data. In other words, signals may already have been picked up by our instruments – although there is still no definitive proof of this–, but that, due to the inefficient methods and algorithms of today, we have overlooked them.
PRESS RELEASE: https://t.co/crfRvTseVz
Will Machine Learning Help Us Find Extraterrestrial Life?Research has applied a deep learning technique to a previously studied dataset of nearby stars and uncovered eight previously unidentified signals of interest. pic.twitter.com/w97LUch3kB
— The SETI Institute (@SETIInstitute) January 30, 2023
It is for this reason that University of Toronto college student Peter Ma, together with the Search Institute for Extra-Terrestrial Intelligence (SETI), Breakthrough Listen, and scientific research institutions around the world, have applied machine learning and intelligence artificially to a previously studied data set of nearby stars.
And to the surprise of the researcher, the novel method has led to the discovery of eight previously unidentified signals of interestaccording to a press release.
Thus, according to the initial results of the new research published in Nature Astronomy, there is a slight possibility that the new method has unearthed non-terrestrial “technosignatures”. That would mean that SETI’s goal of finding signals of extraterrestrial intelligence has been achieved. But the question remains: have we found such signs?
Promising future in the search for extraterrestrial signals
The short answer, for now, is still no. Nonetheless, the new system, which identified 100 times more patterns in the noise worth investigating than had been previously observed, detected eight signals interesting enough to prompt follow-up observations. And all this from a small portion of the recordings of humanity’s radio telescopes.
The data comes from 480 hours of observations of 820 stars by the Robert C. Byrd Green Bank radio telescope.hired by SETI Breakthrough to search for radio waves that may indicate the presence of extraterrestrial civilizations.
“In total, we had searched through 150TB of data for 820 nearby stars, in a dataset that had previously been searched in 2017 using classical techniques, but labeled as lacking interesting signals,” Ma said.
“We are scaling this search effort to 1 million stars today with the MeerKAT telescope and beyond. We believe that work like this will help accelerate the rate at which we are able to make discoveries in our great effort to answer the question of ‘are we alone in the universe?’” he added.
What makes these eight signs interesting?
According to the SETI Institute press release, Ma’s algorithm specifically selected the eight radio signals because, among other factors, they are narrowband. And, according to the statement, “signals caused by natural phenomena tend to be broadband.”
The signals also displayed a number of properties that suggest they are not caused by terrestrial interference, such as the fact that they had non-zero drift rates. Specifically, this means, according to the researchers, that the signals had a slope, which could indicate that the origin of a signal had a certain relative acceleration with our receivers, so it was not local to the radio observatory.
Application of modern machine learning methods
While we haven’t yet found much confirmation that we’re not alone in the universe, this new approach to data analysis may allow researchers to more effectively understand the data they collect and move quickly to re-examine targets.
“These results dramatically illustrate the power of applying modern machine learning and computer vision methods to data challenges in astronomy, resulting in both new detections and increased throughput. Applying these techniques at scale will be transformative for the science of radio technosignatures,” said Cherry Ng, another of Ma’s research advisers and an astronomer at both the SETI Institute and the French National Center for Scientific Research.
Read more:
US accuses Russia of violating key nuclear arms control deal
Gigantic potentially “alien” comet heads towards the Sun
“Putin has found a new scapegoat”: the Russian president’s new offensive against the LGBT community