Machine learning identifies the origin of a Martian meteorite
With new, more advanced telescopes coming online almost every year, the amount of data astronomers are able to collect is staggering – the term petabyte has become more common than ever in my usage these days. And with all this new data comes the same old struggle to process it all. This question is one of the reasons community science projects have become popular over the past two decades. We just needed more eyeballs to find objects like exoplanets and supernovae.
And while community science projects remain popular, one of the hottest research topics these days seems to be machine learning and artificial intelligence. That’s not to say that human researchers are becoming obsolete, but machine learning can free up these researchers for less trivial tasks than looking at thousands of light curves or images of rocks. Now, instead, they can take the best options from the machine learning results and essentially read them back.
Not that we want you all to stop counting rocks. It’s also important work, and not every science project can be solved with machine learning.
But sometimes really crazy science goals can be solved with machine learning, and in a new paper published in Nature Communication, a team of researchers used an algorithm to determine the origin of a Martian meteorite. When I say “origin” I mean the actual crater where the meteorite came from on Mars. Wild, right?
The meteorite is cataloged as NWA 7034 and known informally as “Black Beauty”. It is a brecciated Martian rock, which means that it contains sharp and angular fragments of different types of rock, all cemented together. For those who love geology, this definition makes this meteorite a sedimentary rock.
This sedimentary nature is what makes Black Beauty unusual and special – it’s the only Martian brecciated rock we can study here on Earth. As lead author Anthony Lagain notes: For the first time, we know the geological context of the only Martian brecciated sample available on Earth, 10 years before Return of Mars samples from NASA mission is to return the samples collected by the Rover of Perseverance Currently exploring Jezero Crater.
To understand the origin of Black Beauty, Lagain and his team developed a machine learning algorithm that could analyze a large amount of high-resolution planetary images of Mars to find impact craters. The algorithm used multiple layers of data collected on Mars with a variety of missions to determine where this particular type of rock could be found and ultimately identified the exact crater, now informally named Karratha. Lagain explains the significance of the discovery, stating: Finding the region from which the “Black Beauty” meteorite originated is essential because it contains the oldest Martian fragments ever found, aged 4.48 billion years, and it shows similarities between the very old crust of Mars, aged about 4.53 billion years ago, and that of today. terrestrial continents. The region we identify as the source of this unique Martian meteorite sample is a true window into the planets oldest environment, including Earth, which our planet has lost to plate tectonics and climate change. ‘erosion.
In the future, the team is also adapting this algorithm for use in finding impact craters on the Moon and Mercury. Co-author Gretchen Benedix notes: This will help unravel their geologic history and answer burning questions that will aid future solar system investigations such as the Artemis program send humans to the moon by the end of the decade or the BepiColombo mission, orbiting Mercury in 2025.
And we really can’t wait to see what this latest machine learning algorithm will find. Although, as a reminder, we’ll have more rocks, boulders, and craters to identify when we’re done setting up new community science projects over the break, so stay tuned for those.
Curtin University press release
AU press release
“Early crustal processes revealed by the ejection site of the oldest Martian meteorite”, A. Lagain et al., July 12, 2022, Nature Communications
This story was written for the Daily Space podcast/YouTube series. I want more news from me, Dr. Pamela Gayand Erik Madaus? Check DailySpace.org.
This article was originally published for medium.com.