[npstr]

I'm sure there is plenty of movement visible on all kinds of bridges. We also know that all bridges will fail eventually, so the real value is having a more or less exact prediction _when_ they will fail, not a "we totally saw that coming" after the fact.

[diggan]

> there is plenty of movement visible on all kinds of bridges

Sure, but "the movements in the cluster began to show an atypical pattern with diverging paths" does highlight that even though movements might be common for all bridges, the particular pattern they discovered for this bridge was uncommon.

Agree that the maximum value one could get from a process like that would be "When will this bridge fail?", but better than nothing, is to get a "This bridge looks like it will fail soon".

Besides, could manual human-driven inspections even be able to give a "more or less exact prediction of when a bridge fails"? If not, then at least a somewhat automated way of getting the same answer would be cheaper for local governments to run, and for the cases where it makes sense, send the human bridge inspectors there.

[gwbas1c]

> a "we totally saw that coming" after the fact.

That's not the case, though. This isn't an "I told you so," like the 2022 Pittsburgh bridge collapse. (https://www.ntsb.gov/news/press-releases/Pages/NR20240221.as...)

The study ended 7 days before the collapse, and it only concluded that an on-site inspection is needed:

> Its findings revealed there were significant indicators present prior to the incident to suggest inspection/consultation with on-site engineers would have been necessary.

[globalise83]

This is a random company selling everything from blockchain to big data analysis performing a retrospective analysis of satellite data over a certain period prior to the collapse. In other words it’s a puff piece to promote the capabilities of what sounds like a very dubious firm, not a report of a predictive study.