Slashdot Mirror
New Software Can Predict Landslides Weeks Before They Happen (smithsonianmag.com)
An anonymous reader quotes a report from Smithsonian: Australian researchers may have found a way to detect landslides as far as two weeks in advance, giving residents time to evacuate and engineers the opportunity to shore up slopes. Using AI and applied mathematics they've developed a software that can identify the subtle signs of an impending slide, signs that would be invisible to the naked eye. "Right now, a lot of the predictions [about where landslides will happen] are based on someone's gut instinct on the location," says Antoinette Tordesillas, a professor at the School of Mathematics and Statistics at the University of Melbourne, who co-led the research. "We don't rely on gut instinct. We want to develop an objective method here." To develop the software, Tordesillas and her team used radar data from mining companies, which produce extremely detailed information of the surface movement of slopes. The team took the data and looked for patterns, eventually figuring out which networks of movements indicated unstable locations. They also used data from a landslide-prone Italian volcano to help develop the algorithm. The software can also incorporate data about other landslide risk factors, like rainfall and erosion, making the targeting even more precise. The data used for monitoring can come from radar based on the ground, on satellites or even in drones.
More important, though, is whether it can NOT predict landslides before they DON'T happen.
low rate of false positives is also important
http://www.geoffreylandis.com
There is already open source landslide detection software (one written by NASA). If these "researchers" would contribute to already existing solutions we would be much better off.
Shouldnâ(TM)t there be a more sciency name? Maybe Terrascoota?
More important, though, is whether it can NOT predict landslides before they DON'T happen.
By using Bayesian statistics one ought to be able to more accurately (not absolute accuracy, tho) differentiate the false positives from the real impending danger
He makes a really good point
Predicting Landslides has always been a challenge. Predicting Mudslides less so- just look for spikes in sales of Kahlua and Vodka in college towns.
"That's the way to do it" - Punch
wait for the "nonstory" of tesla bankruptcy and musk suicide
So far every election day every politician and statistician is surprised by the way people vote.
We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
My first thought was of UNIVAC I. :)
Ezekiel 23:20
The issue is, how accurately? Not very, in my case. This system, we do not know yet.
Be sure to make asinine and meaningless claims. Implied in any statement about the ability to predict is the predictions have "high" accuracy. Fuckall can predict anything - as long as no accuracy is required. First there is the time envelope - when will the event happen? Second there is the probability and this might be contingent on the amount of rain (or Earth 'tremors') (rain ground water saturation). If the OP is too GD lazy to include accuracy, and time range, as well as type I & II error rates, then perhaps a different day job would be a better fit.
The detector scans the terrain & if it sees its reflection in a snow-covered hill, the landslide will bring it down
This is so stupid. So what does this mean? Yes, they can predict a landslide so long as prior to that time they predict where one is likely, AND they install equipment to monitor.
So, where do you put your monitoring equipment right now? This is about as brilliant as a 25 watt bulb.
(Conspiracy theories.... gotta love 'em)
File under 'M' for 'Manic ranting'
Because even mountains need to get their rocks off every once in a while.