AI Might Be Able to Predict Earthquake Aftershocks

Saturday, September 1, 2018 - 10:46

Scientists at Harvard and Google have shown how deep learning can help predict aftershock locations more reliably than existing models in a paper published in the journal Nature.

Harvard and Google scientists trained a neural network to look for patterns in a database of more than 131,000 “mainshock-aftershock” events, before testing its predictions on a database of 30,000 similar pairs, ScienceDaily reports.

The deep learning network was significantly more reliable than the most useful existing model, known as “Coulomb failure stress change.” On a scale of accuracy running from 0 to 1 — in which 1 is a perfectly accurate model and 0.5 is as good as flipping a coin — the existing Coulomb model scored 0.583, while the new AI system hit 0.849.

Brendan Meade, a professor of Earth and planetary sciences at Harvard who helped author the paper, told ScienceDaily that the results were promising. “There are three things you want to know about earthquakes,” said Meade. “When they are going to occur, how big they’re going to be and where they’re going to be. Prior to this work we had empirical laws for when they would occur and how big they were going to be, and now we’re working the third leg, where they might occur.”

The success of artificial intelligence in this domain is thanks to one of the technology’s core strengths: its ability to uncover previously overlooked patterns in complex datasets. This is especially relevant in seismology, where it can be incredibly difficult to see connections in the data. Seismic events involve too many variables, from the makeup of the ground in different areas to the types of interactions between seismic plates to the ways energy propagates in waves through the Earth. Making sense of it all is incredibly hard.

The researchers say their deep learning model was able to make its predictions by considering a factor known as the “von Mises yield criterion,” a complex calculation used to predict when materials will begin to break under stress. As Meade tells ScienceDaily, this factor is often used in fields like metallurgy, “but has never been popular in earthquake science.” Now, with the findings of this new model, geologists can investigate its relevance.

Despite the success of this research, it’s far from ready to deploy in the real world. For a start, the AI model only focuses on aftershocks caused by permanent changes to the ground, known as static stress. But follow-up quakes can also be caused by rumblings in the ground that occur later, known as dynamic stress. The existing model is also too slow to work in real-time. This is important, as most aftershocks occur on the first day after a quake occurs, before roughly halving in frequency on each following day.

As Phoebe DeVries, a Harvard postdoc who helped lead the research, told ScienceDaily: “We’re still a long way from actually being able to forecast [aftershocks] but I think machine learning has huge potential here.”

Related News

How Mental Imagery Can Accelerate Learning?

1397/7/23 09:49

AUT to Host Iran FIRA RoboWorldCup Open 2019

1397/7/15 10:23

Amirkabir University of Technology, Japan to Build a Modern Shaking Table

1397/7/8 10:35

Google Launches New Search Engine for Scientists

1397/6/17 09:11

Scientists Are Developing a Device to Harvest Up to 10 Gallons of Drinking Water Per Hour From Thin Air

1397/6/5 16:37

Scientists Identify Acute Neurological Illnesses Using AI

1397/5/23 14:23

Air Pollution Linked to Serious Changes in Heart Structure, Study Shows

1397/5/21 15:27

Egyptian Students Design Car Running on Nothing but Air

1397/5/20 14:27

Shiraz University Researchers Develop A Device That Can Produce Water Out Of Air

1397/5/20 10:28

Researchers Devise a New Machine Learning Model to Isolate the Effects of Age in Predicting Dementia

1397/5/8 11:43

Scientists Develop AI System to Predict IQ From Brain Scans

1397/4/9 15:02

Scientists Develop Computer Program Looks Five Minutes Into the Future

1397/3/27 17:01

Scientists Use AI to Identify, Count, Describe Wild Animals

1397/3/19 10:05

MIT Physicists Develop AI-based Method Could Speed Development of Specialized Nanoparticles

1397/3/12 13:49

China's Museums to Apply AI to Support the Country's Culture and History

1397/2/23 14:56

Google Lets You Talk To Books With Its New AI Tool

1397/1/28 10:49

Shiraz IAU Students Use AI to Make a Wheelchair Autonomous

1397/1/22 15:53

Norway Aviation Aims to Turn Green

1397/1/20 14:37

Microsoft Offers AI Training Courses to the Public

1397/1/15 11:26

MIT Researchers Develop Device Harvests Water From Desert Air

1397/1/5 13:48

AI Spots 7,000 Undiscovered Craters on the Moon

1396/12/27 12:22

Sufian IAU Student Designs Smart Deice Growing Plants

1396/12/27 10:59

Startup to Apply AI to Improve Workplace Communication

1396/12/16 14:25

AI Helps Detect Earthquakes 17 Times More Earthquakes Than Traditional Methods

1396/11/29 13:20

Opinions


Popular News

Latest News