Can we detect major earthquakes months in advance?

A new study reveals that it may be possible to detect major earthquakes several days, or even months, before they strike. The research could ultimately revolutionize earthquake preparedness and response strategies.

A team of researchers led by Professor Társilo Girona of the UAF Geophysical Institute has developed an innovative approach to earthquake prediction. The detection method utilizes advanced technology to monitor subtle seismic shifts that often precede significant tremors.

“Unraveling the precursory signals of potentially destructive earthquakes is crucial to understand the Earth’s crust dynamics and to provide reliable seismic warnings,” noted the researchers.

“Earthquake precursors are ambiguous, but recent experimental studies suggest that robust warning signs may precede large seismic events in the short (day-to-months) term.”

Machine learning can detect earthquake precursors

By detecting low-level tectonic unrest over large areas, the scientists aim to provide earlier and more accurate predictions of when and where major earthquakes might occur.

The research is a convergence of seismic activity studies and machine learning, specifically focusing on earthquake precursors. The UAF team collaborated with geologist Kyriaki Drymoni from Ludwig-Maximilians-Universität in Munich, Germany.

“Our paper demonstrates that advanced statistical techniques, particularly machine learning, have the potential to identify precursors to large-magnitude earthquakes by analyzing datasets derived from earthquake catalogs,” said Professor Girona.

The researchers developed a computer algorithm to scan data for abnormal seismic activity, identifying meaningful patterns that could indicate an impending earthquake.

Case studies from Alaska and California

Girona and Drymoni focused on two major earthquakes: the 2018 Anchorage earthquake with a magnitude of 7.1 and the 2019 earthquake sequence in Ridgecrest, California, which ranged from magnitudes 6.4 to 7.1.

The experts discovered that both seismic shocks were preceded by approximately three months of unusual, low-magnitude regional seismicity. This activity spanned about 15 to 25 percent of Southcentral Alaska and Southern California leading up to each earthquake.

The Anchorage earthquake, which struck on November 30, 2018 at 8:29 a.m., caused significant damage to roads, highways, and buildings.

The researchers found that the probability of a major earthquake occurring within 30 days increased sharply to about 80 percent around three months before the quake.

This likelihood rose to approximately 85 percent just a few days before the event. Similar patterns were observed for the Ridgecrest earthquake sequence, beginning about 40 days before the first quake.

Precursor activity and geological causes

Much of the unrest preceding these major earthquakes was detected as seismic activity with magnitudes lower than 1.5.

Girona and Drymoni propose that the low-magnitude precursor activity could be due to a significant increase in pore fluid pressure within a fault.

“Increased pore fluid pressure in faults that lead to major earthquakes changes the faults’ mechanical properties, which in turn leads to uneven variations in the regional stress field,” explained Drymoni. “We propose that these uneven variations control the abnormal, precursory low-magnitude seismicity.”

Advances in earthquake research

The study demonstrates that machine learning is enabling significant advances in earthquake research. “Modern seismic networks produce enormous datasets that, when properly analyzed, can offer valuable insights into the precursors of seismic events,” noted Professor Girona.

“This is where advancements in machine learning and high-performance computing can play a transformative role, enabling researchers to identify meaningful patterns that could signal an impending earthquake.”

However, the researchers caution against immediately deploying their algorithm in a new region without adequate training grounded in the historical seismicity of the area.

The experts emphasize the importance of testing the method in near-real-time scenarios to identify and address potential forecasting challenges.

Implications for public safety

The ability to produce dependable earthquake forecasts carries profound implications for public safety, disaster preparedness, and economic stability.

“Accurate forecasting has the potential to save lives and reduce economic losses by providing early warnings that allow for timely evacuations and preparation,” said Girona. “However, the uncertainty inherent in earthquake forecasting 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.”

The study is published in the journal Nature Communications.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–