Google And Harvard Use Artifical Intelligence to Predict Earthquake Aftershocks


Although empirical laws, such as Ohmori’s Law and Bath’s Law, have been developed by researchers to detail the probable size and timing of those aftershocks, it has been more challenging to grasp techniques for forecasting their location.

Researchers have been employing artificial intelligence technology to make efforts to find a solution to the problem. Researchers from Google’s AI division and Harvard University have created an AI model capable of predicting the location of aftershocks up to one year after a major earthquake.

The model was trained on 199 major earthquake events, followed by 130,000 aftershocks, and was found to be more accurate than a method used to predict aftershocks today. Having trained the network, they then tested its predictions about aftershocks on 30,000 historical earthquakes, and compared the predictions with the actual aftershocks. Aftershocks included in the dataset used to train the neural network took place in a perimeter that stretches 50 kilometers vertically and 100 kilometers horizontally from each earthquake epicenter.

The concept of employing artificial intelligent neural networks to attempt to predict aftershocks first emerged a number of years ago, during the first of Brendan Meade (a Professor of Earth and Planetary Sciences), two sabbaticals at Google in Cambridge. Meade later partnered with DeVries, who had been employing neural networks to transform high-performance computing code into algorithms with the ability to run on a laptop to focus on aftershocks.

Meade stated, “After earthquakes of magnitude 5 or larger, people spend a great deal of time mapping which part of the fault slipped and how much it moved” and further added, “Many studies might use observations from one or two earthquakes, but we used the whole database … and we combined it with a physics-based model of how the Earth will be stressed and strained after the earthquake, with the idea being that the stresses and strains caused by the main shock may be what trigger the aftershocks.”

Data used to train the model came from noteworthy earthquakes over the past few decades, such as the 2004 Sumatra earthquake, the 2011 earthquake in Japan, the 1989 Loma Prieta earthquake in the San Francisco Bay Area, and the 1994 Northridge earthquake near Los Angeles. The results were published today in the journal Nature. The study was authored by DeVries, alongside Google machine learning researchers Martin Wattenberg and Fernanda Viégas and Google AI recruiting lead Brendan Meade.

According to US Geological Survey seismologist Dr. Elizabeth Cochran, the machine learning-based approach could save a lot of hassles for ‘aftershock chasers’ who travel to earthquake sites to place seismometers in the hopes of understanding a quake and future aftershock activity.