Skip to main content

Google and Harvard made AI to predict earthquake aftershocks!

Earthquake researchers have been trying to model aftershocks for years. By now, they’re able to fairly accurately predict when aftershocks are going to happen, and how large they’ll be. But they’ve been far from perfect when it comes to pinpointing their location.
The answer—of course—appears to be artificial intelligence. A team of collaborators from Google and Harvard team report that after training a neural network, the same kind of AI that powers Facebook photo tagging and Alexa’s voice transcription, on a database of more than 131,000 earthquakes and the locations of their subsequent aftershocks, they’ve come up with the best way yet to predict where future aftershocks will occur.
At its core, artificial intelligence is fancy pattern matching: Show it data, whether pictures of someone’s face or the locations of earthquake aftershocks, and the algorithm will try to find the underlying pattern. For facial recognition that pattern is the pixel arrangements that represent a person’s face, and in aftershock prediction its the equation that can be used to explain the reason for aftershock locations.
Researchers wrote in the paper, published in Nature yesterday (Aug. 29), that one reason for the algorithm’s accuracy is its use of two complex metrics that had not previously been thought to be correlated with aftershocks, called maximum shear stress change and the von-Mises yield criterion. These metrics are commonly applied in the sciences of bendable materials like copper or aluminum, and not used in aftershock prediction—though that might now change.
But don’t get excited that this is going to start helping people tomorrow—as Harvard researcher Phoebe DeVries, coauthor of the paper, candidly told the BBC, “We’re quite far away from having this be useful in any operational sense at all. We view this as a very motivating first step.”

Labels

Labels:

Comments

Post a Comment

Popular posts from this blog

Everything you should know about the coronavirus: COVID-19

  What are coronaviruses? SARS-CoV-2 belongs to a family of single-stranded RNA viruses known as coronaviridae, a common type of virus which affects mammals, birds and reptiles. In humans, it commonly causes mild infections, similar to the common cold, and accounts for 10–30% of upper respiratory tract infections in adults. More serious infections are rare, although coronaviruses can cause enteric and neurological disease. The incubation period of a coronavirus varies but is generally up to two weeks. Previous coronavirus outbreaks include  Middle East respiratory syndrome (MERS ), first reported in Saudi Arabia in September 2012, and severe acute respiratory syndrome (SARS), identified in southern China in 2003. MERS infected around 2,500 people and led to more than 850 deaths while SARS infected more than 8,000 people and resulted in nearly 800 deaths. The case fatality rates for these conditions were 35% and 10%, respectively. SARS-CoV-2 is a new strain of co...
Post a Comment
Read more

The First Step Towards Responsible AI Needs To Be About People Not Strategy!

Article By Charles Radclyffe:  I was recently consulting for an organisation that was looking to implement a framework to govern the implementation of Artificial Intelligence (AI)  technologies. Like many organisations in their sector, they had been running various ‘lab’ experiments for some time, and had seen positive results; but there was still something holding them back from wholesale investment. A major consulting firm had encouraged them to ‘accelerate’ their innovation by using a framework to govern the roll-out. I asked them where they felt it needed more focus, and they responded saying that it felt somewhat vanilla, a re-hashing of any-old IT project management best practice. “Surely there is something different about AI”, they asked? I couldn’t agree more. There is no magic to AI. Today’s AI is a collection of methodologies that apply extreme reductionism to Big Data in order to elicit patterns, calculate probabilities or make predictions. Wha...
Post a Comment
Read more

C3 IoT Partners With Google Cloud On AI and IoT

C3 IoT announced on Tuesday a new strategic partnership with Google Cloud Platform (GCP), aimed at accelerating digital transformation with AI and IoT. C3 IoT announced on Tuesday a new strategic partnership with Google Cloud Platform (GCP), aimed at accelerating digital transformation through the use of artificial intelligence (AI) and the Internet of Things (IoT). As part of the announcement, C3 IoT confirmed its IoT platform has been integrated into GCP, leveraging the cloud platform’s infrastructure and AI capabilities. The businesses will work together on marketing, selling, and training initiatives. “The Google Cloud and C3 IoT partnership creates a solution that dramatically speeds up our customers’ digital transformations to allow them to attain new levels of operational efficiency, productivity, and competitive advantage,” said Ed Abbo, C3 IoT President and CTO. “Together, w...
Post a Comment
Read more