Scientists are using artificial intelligence (AI) to improve data analysis to better understand earthquakes, predict their behavior, and warn of seismic events faster and more accurately.
This research largely relies on neural networks training computers to extract patterns from massive volumes of ground-motion measurements.
Harvard University's Brendan Meade used a neural network to run an earthquake analysis 500 times faster than previously, and with Google researchers also demonstrated the networks' ability to forecast aftershocks.
Dovetailing with this is the notion that smaller and more affordable sensors will enable scientists to collect larger amounts of seismic data, from which new insights could be derived using neural networks and similar AI methods.
Researchers at the California Institute of Technology are employing such solutions to build systems that can more accurately identify earthquakes as they transpire, predicting the location of the epicenter and tremor propagation.
From The New York Times
View Full Article - May Require Paid Subscription
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA