Thanks to Google Cloud: Algorithm finds 27,500 asteroids in old images



The number of recent asteroid discoveries in recent quarters

(Image: B612 Foundation)

Using AI algorithms and Google Cloud resources, a research team has discovered 27,500 previously unknown asteroids without having to make a single new astronomical observation. This is reported by the US organization “B612 Foundation”, which is dedicated to asteroid defense. The candidates that have now been discovered are those that are very likely real asteroids, but this has not yet been finally confirmed.

Advertisement

The research team reports that most of the celestial bodies are located in the asteroid belt between Mars and Jupiter. But there are also said to be over 100 near-Earth asteroids. Overall, more asteroids have already been discovered in the first quarter of 2024 than in the entire previous year, 2023.

According to the statement, the researchers worked with a database that contains millions of astronomical images from the US research facility NOIRLab. They were uploaded to the Google Cloud and then searched by an AI algorithm called THOR (Tracklet-less Heliocentric Orbit Recovery). He related billions of imaged objects to one another and looked for traces that point to asteroids. He found what he was looking for in tens of thousands of cases and the technology met his high expectations. In a first attempt two years ago, the algorithm discovered around 100 previously unknown asteroids.

Asteroids are typically discovered by scanning the same area of ​​the sky multiple times over the course of a night. Celestial bodies within the solar system move on it, creating “tracklets”. On this basis, data on the position and movement of celestial bodies can be determined, which can then be further researched. The THOR algorithm now works without such tracklets and only requires several recordings of a region of the sky taken within a few days. To do this, he connects points of light that match the orbits of asteroids. This allows old collections to be searched for celestial bodies that have not yet been found, as is now the case with the NOIRLab catalog NSC DR2.

The technology should significantly speed up the search for asteroids. It has gained enormous momentum over the past 20 years. The search is primarily for asteroids close to Earth that could pose a threat to our home planet. For the particularly large ones, our picture is already largely complete; for the smaller ones, the number of unreported cases is still expected to be high. But even objects with a diameter of a few hundred meters could cause immense devastation if they hit. The THOR algorithm was developed at the Asteroid Institute of the B612 Foundation. This now wants to search many more catalogs.


(mho)

To home page

source site