​​Expert on Earthquake Prediction Available: Quakes Foretold in Small-Scale Laboratory Experiments Backed by Machine Learning

Article ID: 659660

Released: 24-Aug-2016 11:05 AM EDT

Source Newsroom: Los Alamos National Laboratory

Expert Pitch
  • Credit: Los Alamos National Laboratory

    Geophysicist Paul Johnson is working on predicting earthquakes using machine learning.

Why is predicting earthquakes so hard? Paul Johnson is a geophysicist at Los Alamos National Laboratory who is currently conducting experiments and machine-learning-based data analysis with the goal of forecasting earthquakes. Johnson is a Los Alamos National Laboratory Fellow, a Fellow of the Acoustical Society of America, and an American Geophysical Union Fellow.

In a laboratory setting, Johnson’s team can predict quakes by applying new developments in machine learning, which exploits computer programs that expand and revise themselves based on new data. Machine learning allows the team to identify telltale sounds—much like a squeaky door—that predict when a quake will occur. Because the experiment closely mimics Earth faulting, the same approach may ultimately allow predicting the timing, but not size, of an earthquake. The prediction approach also has far-reaching applications to all failure scenarios including nondestructive testing, brittle failure of all kinds, avalanche, structural health monitoring, failure of machine parts, and more. #ItalyEarthquake


Chat now!