[ExI] earthquake prediction

BillK pharos at gmail.com
Wed Oct 18 17:07:31 UTC 2023

On Wed, 18 Oct 2023 at 17:42, spike jones via extropy-chat
<extropy-chat at lists.extropy.org> wrote:
> Hey cool, I have long wondered if the USGS could give us a warning in time to duck and cover in case of an earthquake.  It seemed to me like it could, given sufficient numbers of detectors and such.  Just a few minutes ago I got a duck and cover notice from them for the first time.  The earthquake is a 5.7 epicenter about 90 km northeast of here.  It is not yet fast enough however, for a quake that size would be nothing by the time the waves travelled this far.  I heard a creak when my house moved a little, then the warning came to the phone a few seconds later.
> In any case… as they set more detectors and the system matures, it can only get better.  So maybe we are getting there.
> spike
> _______________________________________________

Oct 05, 2023
AI-Driven Earthquake Forecasting Shows Promise in Trials

Developed by researchers at The University of Texas at Austin, the AI
algorithm correctly predicted 70% of earthquakes a week before they
happened during a seven-month trial in China.
The AI was trained to detect statistical bumps in real-time seismic
data that researchers had paired with previous earthquakes. The
outcome was a weekly forecast in which the AI successfully predicted
14 earthquakes within about 200 miles of where it estimated they would
happen and at almost exactly the calculated strength.


More information about the extropy-chat mailing list