[tylerni7]

Oh hey I wrote this!

Yeah, we had a detector with some ML stuff, it worked okay, but the main issue is there isn't much training data.

Overall the false positives are quite low (visually, which is hand wavey, of course). I've not really seen a big event that was not real. I ran it for a while 24/7 and while there are "scintillations" there aren't any circular waves. False negatives are a much bigger issue. Something like an IRBM or SRBM doesn't really show up, and those are much more common.

Fwiw, this uses a bandpass filter to look for the ripples, which filters out a ton of noise. Looking at ionospheric depletion would be good and probably more sensitive, but it requires accurate models of what the ionosphere ought to do. I've tried a few things there with mixed results.

[krisoft]

> Oh hey I wrote this!

I’m amazed by your project. Thank you for sharing it with us.

[tylerni7]

Thanks! It's mostly just been for fun, lots of academic work has already shown the principles of it.

I'm glad folks are looking at it, and enjoying it! If you have questions or anything let me know! :)

[krisoft]

You mentioned on twitter[1] that there are realtime data sources which could be used to do the same kind of visualisation/detection.

What would these sources be?

1: https://twitter.com/tylerni7/status/1593466486714421249?s=20...

[tylerni7]

The main protocol is called NTRIP. Lots of sources make it available (though it might be annoying to stream from ~250 simultaneously, not sure). There's a lot if you search that term though.

I think GEONET (the Japanese data source) might have some NTRIP casters. Also some in Korea and elsewhere. Sometimes you have to pay for access though, so I need to look more.

[krisoft]

Thank you very much!