Artificial intelligence finds nearly 30,000 unknown asteroids in existing telescope images

Artificial intelligence is being used to produce more fake images, and scientists are also using it to identify patterns in data that would otherwise be impossible to see. Astronomers also use artificial intelligence to improve image quality and analyze space images. Some artificial intelligence may help save Earth from a catastrophic asteroid.

Although scientists have spent a long time searching for asteroids in space, including in the solar system, finding some has proven very difficult. A new AI algorithm has located about 27,500 asteroids hiding in plain sight in existing telescope images.

like space ReportsThe artificial intelligence algorithm helps scientists track asteroids, some of which may one day collide with Earth.

Many of the newly located asteroids are located in the asteroid belt between Mars and Jupiter. Scientists have already found more than 1.3 million asteroids in this part of the solar system, but somehow, nearly 30,000 of them have not been found yet despite being visible in old close-ups.

Of these asteroids, which were found over the course of about five weeks, 150 have paths that could lead them into Earth’s orbit, although none appear to be headed toward the planet. However, since the asteroid could cause significant damage to Earth — sorry, dinosaurs — advance notice is essential. It’s a big part of ongoing space science, including part of the 3200-megapixel LSST mission statement Petapixel I saw recently.

The new AI algorithm for asteroid tracking is called Recovering the heliocentric orbit without trackingTHOR, or THOR, looked at more than 400,000 archival images of the night sky maintained by the National Infrared Optical Astronomy Research Laboratory (NOIRLab). The algorithm needs five observations over 30 days of a given part of the sky to do its job, and has been trained to analyze up to 1.7 billion points of light in just one image at a time. space.

Scientists scaled THOR using Google Cloud, which is why the team is featured in the Google video above. This approach is also transferable to other datasets.

“Not only can we find asteroids in datasets that were never intended for them, but we can also make every other telescope in the world better at finding asteroids,” says Ed Low, executive director of the Asteroid Institute. “It’s a change in how astronomy works.”

It is a change that may one day protect Earth from disaster.

Image credits: B612 Asteroid Institute/DiRAC Institute at the University of Washington/Open Space Project