Researchers at the University of Alaska Fairbanks have developed a new method that could potentially predict major earthquakes months in advance. The technique uses machine learning to identify abnormal low-magnitude seismic activity that precedes large quakes. Társilo Girona, a research assistant professor at the UAF Geophysical Institute, led the study along with co-author Kyriaki Drymoni from Ludwig-Maximilians-Universität in Munich, Germany.
Their findings were published in the journal Nature Communications on August 28. The researchers focused on two major earthquakes: the 2018 magnitude 7.1 Anchorage earthquake in Alaska and the 2019 Ridgecrest earthquake sequence in California, which ranged from magnitudes 6.4 to 7.1. They discovered that about three months of unusual low-magnitude regional seismicity had occurred across 15% to 25% of Southcentral Alaska and Southern California before each of these earthquakes. Using their data-trained program, Girona and Drymoni found that for the Anchorage earthquake, the probability of a major quake happening within 30 days or less increased abruptly to around 80% approximately three months prior to the event.
This probability further increased to about 85% just days before the earthquake occurred.
AI predicts earthquakes months ahead
Similar probability findings were observed for the Ridgecrest earthquake sequence, starting around 40 days before the onset of the quakes.
The authors propose that the precursory low-magnitude seismic activity is caused by an increase in pore fluid pressure within a fault. High pore fluid pressures can potentially lead to fault slip if the pressure is sufficient to overcome the frictional resistance between the blocks of rock on either side of the fault. While this new method shows promise, the researchers emphasize that their algorithm needs to be tested in near-real-time situations to identify and address potential challenges for earthquake forecasting.
They also caution against employing the method in new regions without first training the algorithm with the area’s historical seismicity data. Girona acknowledges that producing reliable earthquake forecasts has a “deeply important and often controversial dimension.” He notes that accurate forecasting could save lives and reduce economic losses by providing early warnings, but the inherent uncertainty in earthquake prediction also raises significant ethical and practical questions. False alarms can lead to unnecessary panic, economic disruption, and a loss of public trust, while missed predictions can have catastrophic consequences.
As research in this field progresses, scientists hope to provide better tools for earthquake forecasts that can help society while balancing these challenges.
April Isaacs is a news contributor for DevX.com She is long-term, self-proclaimed nerd. She loves all things tech and computers and still has her first Dreamcast system. It is lovingly named Joni, after Joni Mitchell.
