Researchers create an AI treasure map to discover meteorites in Antarctica

Researchers from the Delft University of Technology, the Université libre de Bruxelles, and the Vrije Universiteit Brussel have created a ‘treasure map’ using artificial intelligence and machine learning to pinpoint locations of meteorites in Antarctica. Researchers believe Antarctica could be home to more than 30,000 meteorites.

The researchers combined different types of observations in a machine-learning algorithm to identify potential meteorite-rich zones. Accuracy of over 80% was achieved in unexplored areas, said scientists.

"Through our analyses, we learned that satellite observations of temperature, ice flow rate, surface cover and geometry are good predictors of the location of meteorite-rich areas," said Veronica Tollenaar, one of the researchers from the Université libre de Bruxelles

The researchers were able to find 600 hot spots in Antarctica using the AI. The reports on previous meteorite recovery missions are vague and don’t have much info. This leads to a lack of good-quality labels. To fix this issue, researchers relied on ‘positive and unlabelled learning’. 

Blue ice areas on Antarctica are known to contain meteorites, making it easy to detect and collect them during fieldwork missions, said the researchers.