Tag Archives: aftershock

Amatrice, the epicenter of the 2016 Italian earthquake. Credit: Youtube, Wikimedia Commons.

AI can now predict where an earthquake’s aftershock will hit next

Amatrice, the epicenter of the 2016 Italian earthquake. Credit: Youtube, Wikimedia Commons.

Amatrice, the epicenter of the 2016 Italian earthquake. Credit: Youtube, Wikimedia Commons.

An aftershock is like an echo — a smaller earthquake that occurs soon after a larger one, hitting the same area as the main shock. Large magnitude quakes can generate aftershocks of varying magnitudes over a period of months. For people living and working around the site of an earthquake, the subsequent days and weeks are filled with anxiety — when will there be a new one?

Seismologists have crafted models that fairly accurately predict when an aftershock is going to take place and how violent (i.e. magnitude) it will be. Now, researchers at Google and Harvard have teamed up to produce an artificial intelligence system that can also predict where the aftershock will hit next.

The collaboration devised an AI that was fed a database of 131,000 earthquakes and the location of their subsequent aftershocks. The machine learning algorithm was instructed to spot the patterns in this complex landscape of variables upon variables.

There are a lot of things that shape a seismic event — from the composition of the ground to the interactions between tectonic plates to the ways seismic waves propagate through the Earth. Making sense of all the intricate layers upon layers can be maddening. However, this sort of high-volume pattern matching is what machine learning algorithms excel at. Such AIs are currently being used by tech giants like Facebook, Amazon, and Google to sell you virtual assistants or to show search results.

“After earthquakes of magnitude 5 or larger, people spend a great deal of time mapping which part of the fault slipped and how much it moved,” said Brendan Meade, a Professor of Earth and Planetary Sciences at Harvard University.

“Many studies might use observations from one or two earthquakes, but we used the whole database…and we combined it with a physics-based model of how the Earth will be stressed and strained after the earthquake, with the idea being that the stresses and strains caused by the main shock may be what trigger the aftershocks.”

Meade was first inspired to neural networks to predict aftershocks several years ago during his two sabbaticals at Google in Cambridge. At the time, deep learning algorithms were not as established as they are today but the idea immediately sounded too good to pass.

After years of work, Meade and colleagues came up with a model which has much better predictive power than anything before it. On a scale of accuracy from 0 to 1 — where 1 is a perfectly accurate model and 0.5 is essentially the accuracy of flipping a coin — the new AI system scored 0.849 while the previously most precise model scored only 0.583.

The neural network was able to work so well thanks a little quirk it managed to uncover all by itself. The complex calculations take into consideration a factor known as the “von Mises yield criterion”, which predicts when a material will break under a stress. It’s been mostly used by engineers in the field of metallurgy. Now, it has also found its place in earthquake science, the authors reported in the journal Nature.

“This is a quantity that occurs in metallurgy and other theories, but has never been popular in earthquake science,” Meade said. “But what that means is the neural network didn’t come up with something crazy, it came up with something that was highly interpretable. It was able to identify what physics we should be looking at, which is pretty cool.”

Another advantage of the new AI is that it works for different types of faults. Because it’s generalizable, the system can just as well predict aftershocks around slip-faults, such as those seen in California, or shallow subduction zones, as seen in Japan.

Before you get overly excited though, be aware that this AI has a number of important limitations. The system only works with aftershocks caused by permanent changes to the ground, so-called static stresses. Aftershocks, however, can also be triggered by dynamic stresses that do not permanently change the applied load and thus can trigger earthquakes only by altering the mechanical state or properties of the fault zone.

The AI is also too slow to work in real-time, which is a must-have considering that most aftershocks occur in the first day following an important earthquake.

Going forward, the researchers hope to overcome these challenges one by one. What’s more, Meade also has his mind set to predicting the magnitude of earthquakes themselves — something which is still considered highly esoteric and, perhaps, impossible to do.

“I think there’s a quiet revolution in thinking about earthquake prediction,” he said. “It’s not an idea that’s totally out there anymore. And while this result is interesting, I think this is part of a revolution in general about rebuilding all of science in the artificial intelligence era.

“Problems that are dauntingly hard are extremely accessible these days,” he continued. “That’s not just due to computing power — the scientific community is going to benefit tremendously from this because…AI sounds extremely daunting, but it’s actually not. It’s an extraordinarily democratizing type of computing, and I think a lot of people are beginning to get that.”

Large earthquakes don’t trigger others far away

Simplified map of seismic hazards in the US


Ever since the 9.0 earthquake in Japan, there has been a growing mainstream interest for earthquakes, which will probably fade away as time passes, only to be revived when the next big temblor strikes. However, the good news is that, even for a brief period of time, seismologic studies are given the attention they very much deserve. Such is the case with a study conducted by the Royal Geographic Survey and the University of Texas which concluded that while major earthquakes do, of course, set off strong aftershocks in the nearby vecinity of the epicenter, they won’t have any effect for distances of over 600 miles.

Previous research seemed to indicate that a major earthquake could trigger smaller aftershocks throughout the whole planet, so the team set out to study if this is actually true, by studying seismic data from the past 30 years; they found 205 big earthquakes (with a magnitude of over 7), and no less than 25.222 moderate earthquakes (magnitudes of 5 to 7).

The team checked to see if there was a surge in smaller earthquakes after big ones, and they found out that while moderate earthquakes increase in number after bigger ones, they all take place at less than 400 miles from the major temblor, and in less than 24 hours.

“The regional hazard of larger earthquakes is increased after a mainshock, but the global hazard is not,” the team concludes.

While this is not big news for the seismological community, who would have most definitely noticed a thing like this, the study should go a long way to calming people down after the recent seismic events.

Disturbing time-lapse animation shows Japan earthquakes

The 9.0 (it seems this is the actual magnitude) earthquake that hit Japan on the 11th of March created an absolutely incredible number of aftershocks, some of which were pretty intense on their own. However, a few days before it, as stress built up the subduction area between the Pacific and North American plates, one could easily see some foreshocks too.

The 7.2 temblor, which was one of these foreshocks, struck Japan on March 9, and it was pretty strong on its own; however, since the big earthquake started, aftershocks continue to rattle Japan, and for the past days, pretty much every significant earthquake in the world took place in that area.

Just a few hours after it, there were 19 reported aftershocks, and the estimated number now is over 100. This was the 4th biggest earthquake ever to be recorded, and despite the fact that aftershocks seem to decrease in intensity, there is no indication of them stopping any time soon. Before this, since 1973, there were only 9 earthquakes bigger than 7.0 recorded in Japan – now that number has increased greatly.

Renowned Geophysicist explains Japan tsunami

If you’re looking for an easy to understand scientific explanation about the formation of the devastating quake and tsunami that devastated Japan this Friday, you’d better read Dr. John Ebel‘s theory from below, Professor of geophysics and director of Weston Observatory of Boston College.

“We had an earthquake caused by the Pacific Ocean plate sliding under the Asian plate and as it slides under the Asian plate is pushed up…any time you move the ocean floor up or down you induce a tsunami in the ocean. Tsunamis travel fast when the ocean is deep they travel slowly when the ocean is shallow. When the ocean is deep, the wave spreads out so you have maybe a foot high wave that’s spread out hundreds of miles and it’s traveling at literally 500 miles an hour.”

Dr. Ebel says at those speeds land masses close to the epicenter like the Japanese island of Honshu had only minutes to prepare where as Hawaii and the west coast had hours. “When you get to islands like Hawaii which are thousands of miles away you have hours and hours of warning…they had about 6 or 8 hours of warning.”

Just like a single rain drop spreads across a pond a tsunami circumnavigates the globe. “Tide gages for instance in Mobile Bay and on the Gulf coast will register a very small recording probably tonight or early tomorrow morning from this tsunami. It will spread through all the ocean basins.”

On the same wavelength, Dr. Ebel says that it’s very possible strong aftershocks could be experienced within the next few days or weeks. Some could even be large enough that another small tsunami is generated…