Machine learning-detected signal predicts time to earthquake

December 18, 2018 by Nancy Ambrosiano, Los Alamos National Laboratory
Los Alamos National Laboratory researchers applied machine-learning expertise to predict quakes along Cascadia, a 700-mile-long fault from northern California to southern British Columbia that flanks cities such as Seattle. The results are published today in two papers in Nature Geoscience. Credit: Los Alamos National Laboratory

Machine-learning research published in two related papers today in Nature Geoscience reports the detection of seismic signals accurately predicting the Cascadia fault's slow slippage, a type of failure observed to precede large earthquakes in other subduction zones.

Los Alamos National Laboratory researchers applied machine learning to analyze Cascadia data and discovered the megathrust broadcasts a constant tremor, a fingerprint of the fault's displacement. More importantly, they found a direct parallel between the loudness of the fault's acoustic signal and its physical changes. Cascadia's groans, previously discounted as meaningless noise, foretold its fragility.

"Cascadia's behavior was buried in the data. Until machine learning revealed precise patterns, we all discarded the continuous signal as noise, but it was full of rich information. We discovered a highly predictable sound pattern that indicates slippage and fault failure," said Los Alamos scientist Paul Johnson. "We also found a precise link between the fragility of the fault and the signal's strength, which can help us more accurately predict a megaquake."

The new papers were authored by Johnson, Bertrand Rouet-Leduc and Claudia Hulbert from the Laboratory's Earth and Environmental Sciences Division, Christopher Ren from the Laboratory's Intelligence and Space Research Division and collaborators at Pennsylvania State University.

Machine learning crunches massive seismic data sets to find distinct patterns by learning from self-adjusting algorithms to create decision trees that select and retest a series of questions and answers. Last year, the team simulated an earthquake in a laboratory, using steel blocks interacting with rocks and pistons, and recorded sounds that they analyzed by machine learning. They discovered that the numerous , previously discounted as meaningless noise, pinpointed when the simulated fault would slip, a major advance towards earthquake prediction. Faster, more powerful quakes had louder signals.

The team decided to apply their new paradigm to the : Cascadia. Recent research reveals that Cascadia has been active, but noted activity has been seemingly random. This team analyzed 12 years of real data from seismic stations in the region and found similar signals and results: Cascadia's constant tremors quantify the displacement of the slowly slipping portion of the subduction zone. In the laboratory, the authors identified a similar signal that accurately predicted a broad range of fault failure. Careful monitoring in Cascadia may provide new information on the locked zone to provide an early warning system.

Explore further: Machine learning used to predict earthquakes in a lab setting

More information: Claudia Hulbert et al. Similarity of fast and slow earthquakes illuminated by machine learning, Nature Geoscience (2018). DOI: 10.1038/s41561-018-0272-8

Bertrand Rouet-Leduc et al. Continuous chatter of the Cascadia subduction zone revealed by machine learning, Nature Geoscience (2018). DOI: 10.1038/s41561-018-0274-6

Related Stories

Machine learning used to predict earthquakes in a lab setting

October 23, 2017

A group of researchers from the UK and the US have used machine learning techniques to successfully predict earthquakes. Although their work was performed in a laboratory setting, the experiment closely mimics real-life conditions, ...

Recommended for you

Apple pivot led by star-packed video service

March 25, 2019

With Hollywood stars galore, Apple unveiled its streaming video plans Monday along with news and game subscription offerings as part of an effort to shift its focus to digital content and services to break free of its reliance ...

How tree diversity regulates invading forest pests

March 25, 2019

A national-scale study of U.S. forests found strong relationships between the diversity of native tree species and the number of nonnative pests that pose economic and ecological threats to the nation's forests.

Scientists solve mystery shrouding oldest animal fossils

March 25, 2019

Scientists from The Australian National University (ANU) have discovered that 558 million-year-old Dickinsonia fossils do not reveal all of the features of the earliest known animals, which potentially had mouths and guts.

Earth's deep mantle flows dynamically

March 25, 2019

As ancient ocean floors plunge over 1,000 km into the Earth's deep interior, they cause hot rock in the lower mantle to flow much more dynamically than previously thought, finds a new UCL-led study.

3 comments

Adjust slider to filter visible comments by rank

Display comments: newest first

Nik_2213
5 / 5 (1) Dec 18, 2018
Not quite as ominous as a grumbling volcano developing harmonic tremor, but very interesting. Hopefully, they'll get 'end stage' data without too many casualties...
Anonym
3 / 5 (2) Dec 18, 2018
"Meaningless noise" is redundant.
Nik_2213
5 / 5 (1) Dec 19, 2018
#A. radio fuzz was 'meaningless' until it was identified as CMB, up-ending Cosmology...

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.