by More than 27,000 asteroids in our solar system have been observed in existing telescope images – but thanks to a new AI-powered algorithm, we now have a catalogue. The scientists behind the discovery say the tool makes it easier to find and track millions of asteroids, including potentially dangerous ones that could strike. World one day. It is for those threatening space rocks that the world would previously have needed years of advance warning trying to deflect them away from our planet.
Most of the newfound asteroids hover in asteroid belt between Mars and Jupiter, where scientists have already cataloged more than 1.3 million such rock fragments over the past 200 years. The latest bounty, discovered in about five weeks, also includes about 150 space rocks with their glide paths within Earth’s orbit; to be clear, however, none of these “near-Earth asteroids” appear to be on a collision course with our planet. There are other people Troy which follows Jupiter in its orbit around the sun. The observations of these asteroids have yet to be submitted to and accepted by the Minor Planet Center of the International Astronomical Union, the official body responsible for asteroid discoveries.
Astronomers typically discover new constellations by studying pockets of our sky over and over again, through telescope images collected multiple times each night—usually every few hours. While planets, stars and galaxies in the background do not change from one image to the next, asteroids are observed as specks of light that move significantly, flagged and then verified. From there, the orbits of these asteroids are determined and monitored.
Related: How AI Could Help Find Alien Planets and Asteroids
“This is really a job for AI,” Ed Lu, executive director of the Asteroid Institute and co-founder of the B612 Foundation, said early last month during a discussion of the discovery. In fact, AI tools designed for asteroid searches are already approaching human-reachable levels, Lu said: “I think we’ll quickly surpass that in the coming weeks.”
The algorithm developed by Lu’s team, called Tracklet-less Orbit Recovery Heliocentric, or THOR, analyzed more than 400,000 archival images of the sky maintained by the National Optical-Infrared Astronomy Research Laboratory, or NOIRLab. As long as there are about five observations in 30 days related to the same pocket of the sky, the algorithm can start working. It is trained on a large data set that allows it to analyze as many as 1.7 billion points of light in a single telescope image. It’s designed to scope and connect a point of light from one image of the sky to another in a different image, and determine whether the two specs represent the same object — more often than not, indicating an asteroid moving through the space, according to the description of the algorithm by the B612 Foundation.
“We don’t have a telescope, we don’t operate a telescope,” Lu said during the discussion. “We’re doing this from a data science perspective.”
The scientists scaled their algorithm using Google Cloud, whose computing and data storage services made it easier for the scientists to test thousands of candidate asteroid orbits, according to a statement released by the B612 Foundation on Tuesday (April 30).
“Not only can we find asteroids in a data set that was never meant for, but we can outperform every other telescope in the world at finding asteroids,” Lu said during the talk. “It’s changing the way astronomy is done.”
In 2022, the same team of scientists used THOR to discover 100 asteroids that had not been detected in previous telescope images. Other teams of astronomers have also leveraged AI to find new asteroids. Two weeks ago, for example, citizen scientists were in charge of training an algorithm that led to the discovery of 1,000 new asteroids in archive images clicked by the Hubble Space Telescope. Last July, software called HelioLinc3D designed to search for near-Earth asteroids discovered a 600-foot-wide (180-meter-wide) space rock that is expected to come within 140,000 miles. (225,000 kilometers) of Earth. That is closer than the average distance between our planet and the moon.
Related Stories:
— Citizen scientists and AI go on a cosmic journey to discover 430,000 new galaxies
— How do we know what the Milky Way looks like?
— The Milky Way galaxy could have a different shape than we thought
Scientists have seen more than 2,000 such “potentially hazardous asteroids” so far and it is estimated that around 2,000 more are yet to come. One of the tasks of the Vera C. Rubin Observatory in Chile is to detect these space rocks in an effort to help protect the planet, for which the asteroid-hunting HelioLinc3D software was developed.
The 8.4-meter telescope, scheduled to begin operations next year, will take images of the southern sky every night for at least a decade, with each image covering 40 full moons. Scientists say this end, supported by AI-based software like THOR and HelioLinc3D, could help the observatory find as many as 2.4 million asteroids – double those now cataloged – in its first six months of operations.
