Using machine learning to find space rocks in Antarctica

In some areas, rocks are exposed on the surface. Here, searches for meteorites are done on foot. Credit: 2019-2020 BELARE Meteorite Recovery Expedition Field Team on the Nansen Ice Field

A team of researchers from the Free University of Brussels, the Delft University of Technology and the Vrije Universiteit Brussel have used AI technology to find meteorites hidden in the Antarctic ice. The group describes how their AI system works and what it has shown them so far in the log Scientists progress.

Previous research has shown that large numbers of meteorites regularly strike the earth; two-thirds of all recoveries occur in Antarctica. This is because the continent is covered in ice and preserves them. Plus, their dark coloring tends to stand out. Previous research has shown that most of these meteorites land on snow-covered ice, where they become embedded and covered in more snow. Over time, as ice builds up, it slowly moves to the ocean, where meteorites fall to the sea floor. But other meteorites end up in ice that migrates less and has a texture different. Known as blue ice, it can harbor relatively easily recoverable meteorites. Most meteorites found in Antarctica have been found in blue ice. To date, the means of finding such meteorites involves educated guessing and random wandering, which researchers say isn’t very efficient. In this new effort, they used a machine learning application to narrow down the search.

To apply an AI system to the task, the researchers trained it with satellite data spanning the entire continent, as well as data showing where blue ice fields containing meteorites have been found. They helped the system by adding information about sites that produced meteorites, such as temperature and ice conditions. They then used the system to search the icy continent for areas that met the criteria for probable meteorite sites and found it to be around 83% accurate. He also found over 600 potential areas which he marked for further review by team members in the field. They note that many of the areas discovered were relatively close to research stations.

An exceptionally large meteorite found on the Nansen Blue Ice Area, near the Belgian Antarctic Research Station Princess Elisabeth. Credit: Harry Zekollari

The researchers suggest that the new AI tool, combined with the use of drones, should find many meteorites in the coming years, which they say should help scientists better understand the system’s history. solar.

  • Illustration of the mechanism linked to the flow and ablation of ice (red arrows) which concentrates meteorites in the so-called blue ice zones in Antarctica. Credits: Veronica Tollenaar

  • Using machine learning to find space rocks in Antarctica

    Infographic illustrating the concept of the methods used in the study. Antarctic meteorites are found in areas where blue-colored ice is exposed on the surface (unlike snow). Indirect satellite observations (such as ice flow velocity and surface temperature) predict which areas of blue ice contain meteorites. Credits: Veronica Tollenaar

  • Using machine learning to find space rocks in Antarctica

    “Treasure map” to find meteorites in Antarctica. Also indicates Antarctic research stations (as listed by COMNAP, Credits: Veronica Tollenaar

Evidence of water movement found in meteorites that only recently fell to Earth

More information:

Veronica Tollenaar et al, Unexplored Antarctic Meteorite Collection Sites Revealed by Machine Learning, Scientists progress (2022). DOI: 10.1126/sciadv.abj8138

© 2022 Science X Network

Using machine learning to find space rocks in Antarctica (2022, January 27)
retrieved 27 January 2022

This document is subject to copyright. Other than fair use for purposes of private study or research, no
any part may be reproduced without written permission. The content is provided for information only.

Read the original article here

Disclaimer! Verve Times is an automatic aggregator of all media in the world. In each content, the hyperlink to the main source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the content owner and do not want us to publish your materials, please contact us by email – [email protected]. Content will be deleted within 24 hours.

Sherry J. Basler