Machine-learning earthquake prediction in lab shows promise

August 30, 2017
Researchers at Los Alamos National Laboratory have developed a two-dimensional tabletop simulator that models the buildup and release of stress along an artificial fault. In this image, the simulator is viewed through a polarized camera lens, photo-elastic plates reveal discrete points of stress buildup along both sides of the modeled fault as the far (upper) plate is moved laterally along the fault. Credit:Los Alamos National Laboratory

By listening to the acoustic signal emitted by a laboratory-created earthquake, a computer science approach using machine learning can predict the time remaining before the fault fails.

"At any given instant, the noise coming from the lab zone provides quantitative information on when the fault will slip," said Paul Johnson, a Los Alamos National Laboratory fellow and lead investigator on the research, which was published today in Geophysical Research Letters.

"The novelty of our work is the use of machine learning to discover and understand new physics of failure, through examination of the recorded auditory signal from the experimental setup. I think the future of earthquake physics will rely heavily on machine learning to process massive amounts of raw seismic data. Our work represents an important step in this direction," he said.

Not only does the work have potential significance to earthquake forecasting, Johnson said, but the approach is far-reaching, applicable to potentially all failure scenarios including nondestructive testing of industrial materials brittle failure of all kinds, avalanches and other events.

Machine learning is an artificial intelligence approach to allowing the computer to learn from new data, updating its own results to reflect the implications of new information.

The technique used in this project also identifies new signals, previously thought to be low-amplitude noise, that provide forecasting information throughout the earthquake cycle. "These signals resemble Earth tremor that occurs in association with slow earthquakes on tectonic faults in the lower crust," Johnson said. "There is reason to expect such signals from Earth faults in the seismogenic zone for slowly slipping faults."

Machine learning algorithms can predict failure times of laboratory quakes with remarkable accuracy. The acoustic emission (AE) signal, which characterizes the instantaneous physical state of the system, reliably predicts failure far into the future. This is a surprise, Johnson pointed out, as all prior work had assumed that only the catalog of large events is relevant, and that small fluctuations in the AE signal could be neglected.

To study the phenomena, the team analyzed data from a laboratory fault system that contains fault gouge, the ground-up material created by the stone blocks sliding past one another. An accelerometer recorded the acoustic emission emanating from the shearing layers.

Following a frictional failure in the labquake, the shearing block moves or displaces, while the gouge material simultaneously dilates and strengthens, as shown by measurably increasing shear stress and friction. "As the material approaches failure, it begins to show the characteristics of a critical stress regime, including many small shear failures that emit impulsive acoustic emissions," Johnson described.

"This unstable state concludes with an actual labquake, in which the shearing block rapidly displaces, the friction and shear stress decrease precipitously, and the gouge layers simultaneously compact," he said. Under a broad range of conditions, the apparatus slide-slips fairly regularly for hundreds of stress cycles during a single experiment. And importantly, the signal (due to the gouge grinding and creaking that ultimately leads to the impulsive precursors) allows prediction in the laboratory, and we hope will lead to advances in prediction in Earth, Johnson said.

Explore further: Megathrust quake faults weaker and less stressed than thought

More information: "Machine learning predicts laboratory earthquakes," Geophysical Research Letters (2017). DOI: 10.1002/2017GL074677

Related Stories

Megathrust quake faults weaker and less stressed than thought

September 10, 2015

Some of the inner workings of Earth's subduction zones and their "megathrust" faults are revealed in a paper published today in the journal Science. U.S. Geological Survey scientist Jeanne Hardebeck calculated the frictional ...

How friction evolves during an earthquake

August 15, 2017

By simulating earthquakes in a lab, engineers at Caltech have documented the evolution of friction during an earthquake—measuring what could once only be inferred, and shedding light on one of the biggest unknowns in earthquake ...

Researchers reproduce mechanism of slow earthquakes

March 31, 2016

Up until now catching lightning in a bottle has been easier than reproducing a range of earthquakes in the laboratory, according to a team of seismologists who can now duplicate the range of fault slip modes found during ...

Slow earthquakes may foretell larger events

August 15, 2013

Monitoring slow earthquakes may provide a basis for reliable prediction in areas where slow quakes trigger normal earthquakes, according to Penn State geoscientists.

Earthquake 'memory' could spur aftershocks

January 3, 2008

Using a novel device that simulates earthquakes in a laboratory setting, a Los Alamos researcher and his colleagues have shown that seismic waves—the sounds radiated from earthquakes—can induce earthquake aftershocks, ...

Recommended for you

The world needs to rethink the value of water

November 23, 2017

Research led by Oxford University highlights the accelerating pressure on measuring, monitoring and managing water locally and globally. A new four-part framework is proposed to value water for sustainable development to ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.