Seismic waves reveal giant structures deep beneath Earth's surface | Hacker News Reader

Seismic waves reveal giant structures deep beneath Earth's surface

newscientist.com

85 pointsrbanffy13 comments

> The shear wave echoes from a single seismogram are difficult to distinguish from random noise, so the researchers used a machine-learning algorithm originally designed for identifying trends in large astronomy data sets.

How does one convince oneself that such a machine-learning algorithm is finding genuine signal in the noise, rather than just generating echoes of its training data?

Though I don't know for this one, a semi-common strategy is to use ML to efficiently search for "interesting" datapoints, and then verify with conventional tools.

In that sort of use, it doesn't really matter if it's hallucinating - it'll just produce a lot of false-positives and you'll go (╯°□°)╯︵ ┻━┻ and try something else instead.

Anything generating a lot of possible ‘interesting’ datapoints is very tricky to statistically validate. Essentially you need to raise the threshold for statistical significance based on the number of possibilities being considered.

That’s almost never done correctly, and often misused. https://en.wikipedia.org/wiki/Data_dredging

I asked this question if it really was Machine Learning last time this was posted and I don't think it was (Feel free to correct me)

It's - http://sequencer.org/

Pseudo-code - http://sequencer.org/static/images/image1.png

I find it much more exciting than ML because it's both real and seems to be a simple online service for scientists, which is pretty cool.

A video on it - https://www.youtube.com/watch?v=KN-N7l5spmE

On a cursory look it seems to construct a distance matrix between all pairs of items, and look for a spanning tree with that distance metric that is "elongated" - i.e., less branching. Straightforward enough.

There seems to be a bit more, involving iterating over different scales and over different distance metrics, but that's not particularly principled or efficient.

The github has a good overview of the algo(and clean python code): https://github.com/dalya/Sequencer

https://en.wikipedia.org/wiki/Phlegraean_Fields

Does lower S-wave velocity imply high-viscosity liquid?

And might that be due to water? Maybe oceanic crust carried by deep convection?

Creatures moving through solid rock...

The Devil in the Dark?

Sorry I can't remember! I was thinking of a short story by either Clarke or Asimov

I'm a doctor, not a bricklayer!

I blame the Mayans.

Reply on news.ycombinator.com