meta_pixel
Tapesearch Logo
Log in
Nature Podcast

04 July 2019: Machine learning in materials science, and sand’s sustainability

Nature Podcast

podcast@nature.com

News, Science, Technology

4.5893 Ratings

🗓️ 3 July 2019

⏱️ 23 minutes

🧾️ Download transcript

Summary

This week, using an algorithm to find properties in materials science, and the global consequences of sand-mining.


In this episode:


00:47 Predicting properties

A word-association algorithm is reading millions of abstracts to discover new properties of materials. 

Research article: Tshitoyan et al.News and Views: Text mining facilitates materials discovery


08:28 Research Highlights

Tiny robot-jellyfish, and genome mutation hot-spots. 

Research Article:Multi-functional soft-bodied jellyfish-like swimmingResearch Highlight:How DNA ‘hotspots’ snarl the search for cancer genes


10:48 Sand under strain

Researchers warn that the mining of sand is unsustainable. 

Comment:Time is running out for sand


15:44 News Chat

The results of a bullying survey, and the spread of microbial disease through opioid use. 

News: Germany’s prestigious Max Planck Society conducts huge bullying surveyNews: The US opioid epidemic is driving a spike in infectious diseases


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

Transcript

Click on a timestamp to play from that location

0:00.0

Nature.

0:02.0

In an experiment, I don't know yet.

0:06.0

Why is Blight so far?

0:08.0

Like, it sounds so simple.

0:09.0

They had no idea.

0:11.0

But now the data's...

0:12.0

I find this not only refreshing, but at some level astounding.

0:20.0

Nature.

0:25.7

Welcome back to the Nature podcast.

0:30.7

This week we'll be finding out how computers can predict the properties of materials and hearing about the environmental impacts of sand mining.

0:35.3

I'm Benjamin Thompson and I'm Nick out.

0:46.7

First up, I want to talk about making stuff.

0:51.1

Material science is a field all about creating the cutting edge, combining existing compounds

0:57.0

and discovering new ones. But with so many different ways of going about it, it could be

1:03.0

hard to know where to start. To discover an original material or even repurpose an old one with new

1:10.0

properties requires a lot of experimentation,

1:14.1

with a little bit of luck. But this week in nature, researchers have been applying a machine learning

1:20.3

algorithm known as word to veck to try and streamline the discovery process of finding materials

1:27.1

with new properties.

1:29.3

This algorithm is known as unsupervised, meaning that it has no knowledge of what anything might mean.

1:36.3

It discovers that through associations.

1:39.3

In this case, the algorithm scanned millions of research paper abstracts to try and find meaning.

...

Please login to see the full transcript.

Disclaimer: The podcast and artwork embedded on this page are from podcast@nature.com, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of podcast@nature.com and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.

Copyright © Tapesearch 2026.