Machine learning helps geoboffins spot huge beds of hot rocks 1,000km across deep below Earth's surface

Large structures were detected as anomalies in seismic waves processed by an algorithm

18 Got Tips?

Geophysicists have uncovered large swathes of hot, dense rock lying nearly 3,000 kilometers beneath Earth's surface, hidden below the Pacific Ocean, thanks to an unsupervised learning algorithm.

These structures, described as "ultralow-velocity zones" (ULVZs) in a study published in Science on Friday, were detected by measuring the echoes of seismic waves emitted from earthquakes underground. "Ultralow-velocity zones are areas of unusually dense, hot material at the core-mantle boundary," Doyeon Kim, first author of the paper and a scientist at Cornell University, explained to The Register: "Seismic waves travel up to 30 per cent slower in ULVZs than through surrounding mantle materials."

The reflections of these seismic signals reveal that there are obstacles in the way as the waves travel in between the source of the earthquake and reach the seismometer. By studying the recordings and measuring the amount of diffraction in the echoes, the researchers can estimate how dense or large these objects are.

"We found echoes on about 40 per cent of all seismic wave paths," said Vedran Lekić, co-author of the study and an associate professor of geology at the University of Maryland. "That was surprising because we were expecting them to be more rare, and what that means is the anomalous structures at the core-mantle boundary are much more widespread than previously thought."

Some of the large areas of rock had previously been discovered, but there were new regions that haven't been seen before, like the one lurking below the Marquesas Islands, a tiny group of volcanic islands in the middle of the Southern Pacific Ocean. The team also found that the ultralow-velocity zone underneath the Hawaiian Islands is much larger than previously thought.

"The scale of typical ULVZs found elsewhere are on the order of about 100km. But what we discuss in our paper is an order of magnitude larger than those typical ULVZs, a structure about 1,000km across. ULVZs of this extraordinary size are called 'mega-ULVZs'. We detected two mega-ULVZs, one beneath Hawaii and the other beneath Marquesas Islands, both are located near the edge of the Pacific LLSVPs," Kim told us.

The team collected 7,000 seismogram recordings of the echoes and fed them to a machine-learning algorithm known as Sequencer. Developed by researchers at Tel Aviv University and John Hopkins University, the algorithm uses unsupervised learning to "reveal the main trend or sequence in a dataset." In other words, Sequencer is good at highlighting any anomalies – or the echoes – in data.

"Machine learning in earth science is growing rapidly and a method like Sequencer allows us to be able to systematically detect seismic echoes and get new insights into the structures at the base of the mantle, which have remained largely enigmatic," said Kim.

The researchers don't know what these structures are made out of and how they might affect Earth's plate tectonics over time. "Although still enigmatic we think all of these lower mantle structures are somewhat dynamically related as our mantle convects and the Earth keeps cooling down," he concluded.

"This mantle convection is the driving mechanism for hotspot volcanism and plate tectonics. And the Earth is the only terrestrial planet in our solar system where we uniquely observe plate tectonics and rarely observe such manifestation of volcanisms seen from the surface. Therefore, understanding mantle structures and their characteristics is important to learn how the Earth has evolved or evolving as opposed to other planets." ®

Sign up to our NewsletterGet IT in your inbox daily


Keep Reading

Pack your bags! Astroboffins spot 24 'superhabitable' exoplanets better than Earth at supporting complex life

Just a short 100 or more light years away

Don't panic: An asteroid larger than the Empire State Building is flying past Earth this weekend but we're just fine

2002 NN4 will visit us fairly frequently, and always miss - ignore the clickbait

FYI: Mind how you go. We're more or less oblivious to 75% of junk in geosynchronous orbits around Earth

What a load of rubbish

US military whips out credit card for unmanned low-Earth-orbit outpost prototype (aka a repurposed ISS cargo pod)

Pentagon can't wait to do some 'experimentation and testing' in space

Good news: NASA boffins spot closest near-Earth asteroid ever. Bad news: We never saw it coming. Good news: It's also really small

Thing was the size of a car, moved at 12km/sec, missed us by just 2,950km

We've heard of littering but this is ridiculous: Asteroid dumps up to 50 quadrillion kg of space dirt on Earth, Moon

Sadly, missing all of us by 800 million years

Gamers are replacing Bing Maps objects in Microsoft Flight Simulator with rips from Google Earth

So much for showcasing Redmond's Chocolate Factory alternative

Everything's falling apart. The Moon is slowly rusting up – and it's probably Earth's fault

We're not talking about the programming language, either

Aww, a cute mini-moon is orbiting Earth right now. But like all good things, it too will abandon us at some point

Vid Elon Musk confirms car-sized space rock isn't his Tesla Roadster

Quick Q: Er, why is the Moon emitting carbon? And does this mean it wasn't formed from Theia hitting Earth?

Decades-old theory may require a rethink thanks to Japanese probe

Tech Resources

Webcast Slide Deck | Zero trust strategies to zap ransomware peril

Join industry veteran and security pro Mike Wronski of Nutanix as he explains to Tim Phillips about zero trust strategies combined with HCI can improve your security posture, defend against threats, help prevent your business from being the next victim of ransomware.

Securing Virtual Workforces

Right now, many security teams are struggling to adjust to a virtual workforce and the new requirements that come along with that.

IBM and Nvidia® Solutions Power Insights with the New AI

IBM is well-positioned to help organizations incorporate high-performance solutions for AI into the enterprise landscape.

2020 SANS Remote Workers Poll

See how the tech workforce has adapted to work-from-home and how organizations have navigated the new challenges posed