Machine Learning

3min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

Researchers are using artificial intelligence to try and find meteorites that have fallen from space. The first time they've actually recovered a bit of meteorite from a sort of drone assisted, machine learning assisted technique. That was josh bluminstock from the university of california berkeley. To find out more about this study, there'll be a link to the paper in the show notes.

00:45 A flexible, wearable, fabric microphone

Inspired by the ear, a team of researchers have developed an acoustic fibre that can be woven into fabrics to create a sensitive microphone. This fabric microphone is capable of detecting human speech and heartbeats, and the team think it could be used to develop new, wearable sensors for long-term health monitoring.

Research article: Yan et al.

News and Views: A smart sensor that can be woven into everyday life

08:38 Research Highlights

How a shark’s posture lets you know if it’s asleep, and the desert dust that helps cirrus clouds form.

Research Highlight: The secrets of shark sleep

Research Highlight: Wispy clouds are born of dust in the wind

11:31 How AI helped Togo target financial aid

Early in the COVID-19 pandemic, the government of Togo needed to distribute financial aid to citizens most in need of assistance. As running a nationwide survey to find out people’s financial situations was impossible, they turned to machine learning to discover how best to distribute aid.

Research article: Aiken et al.

19:02 Briefing Chat

We discuss some highlights from the Nature Briefing. Using machine learning to find meteorite fragments in a desert, and using radiocarbon dating to detect forged paintings.

Physics World: ‘Huge leap’ as scientists report first drone-assisted space rock recovery after observed meteorite fall

Nature: Police rely on radiocarbon dating to identify forged paintings

Subscribe to Nature Briefing, an unmissable daily round-up of science news, opinion and analysis free in your inbox every weekday.

Hosted on Acast. See acast.com/privacy for more information.