A new technique that analyses seismic signals can predict days in advance when the most dangerous volcano in the United States will erupt.
Mount St. Helens, located in Washington state, has recently shown signs of recharging and scientists have developed a machine learning tool to find patterns of volcanic activity and provide better emergency plans.
The system was able to determine when the volcano experienced periods of unrest, pre-eruptive and eruptive.
Using the data, the technology predicted at least three days in advance when the volcano would erupt, with 95 percent accuracy.
The study comes less than 10 days after the Pacific Northwest Seismic Network said it had detected 350 earthquakes in the region since February, signs the volcano may be awakening.
A new technique that analyzes seismic signals from Mount St. Helens could predict when America’s most dangerous volcano will erupt days before it happens.
Earlier this month, experts recorded 38 earthquakes around the 8,300-foot volcano, with many of them occurring about 4.6 kilometers below the crater floor.
Specialized teams also detected that magma has been flowing through chambers deep underground, causing the volcano to recharge.
There are fears that the earthquakes could cause another massive explosion reminiscent of the 1980s eruption that left 57 people dead and permanently altered the area’s ecosystem.
But scientists at the University of Granada in Spain have discovered a way to predict a future eruption.
The machine learning tool analyzed all seismic signals during Mount St. Helens’ activity, discovering patterns of progression from one phase to another and changes that indicate it could be moving from a state of unrest to a pre-eruptive state.
Scientists identified 12 parameters using a new machine learning tool, allowing them to create a timeline of past volcanic activity and observe patterns that indicate periods of unrest, pre-eruption and eruption.
The data revealed that pre-eruption signs included tremors, which have been observed this year, and significant magma buildup and pressure buildup.
The 2024 earthquakes are thought to have been caused by pressurization of the magma transport system, which in turn is triggered by the arrival of additional magma, a process called recharge.
Pre-eruption signals also led to the 2004 eruption of Mount St. Helens, when a plume of ash and steam was sent 10,000 feet above the surface.
“This is a reliable numerical value for stating the probability of a volcanic eruption occurring in the short term and would improve monitoring of a volcanic system and the ability to forecast an eruption,” the team shared in the journal. Frontiers in Earth Sciences.
Earlier this month, experts recorded 38 earthquakes around the 8,300-foot volcano in Washington state, with many of them occurring about 4.6 kilometers below the crater floor.
The system predicted at least three days in advance when the volcano would erupt, with 95 percent accuracy.
‘The probability of being in an eruptive state often rises to 80 percent when a volcanic eruption is about to begin, demonstrating that the methodology has potential as a universal monitoring tool.’
For the study, the team used mathematical formulas to analyze parts of the earthquake signals, allowing them to calculate four key characteristics: energy, a measure of predictability, how sharp the signal’s peaks are, and changes in the signal’s frequency.
That data was then categorized into three states, including unrest, when a volcano shows activity but nothing suggesting an eruption.
The next category was pre-eruptive, meaning there is a high probability of eruption and then eruptive, when the volcano explodes.
And the machine learning tool went to work to discover the patterns, which the team ran five times to ensure accuracy.
In 1980, small earthquakes were recorded around Mount St. Helens just before the deadly eruption.
On May 18, 1980, residents flooded the area, sitting in open fields and on rooftops as rumors of a volcanic eruption spread. Millions of people around the world waited for two months to see what would happen next.
But that morning, at 8:32, the results turned out to be deadly as a magnitude 5 earthquake occurred, causing the volcano to lose its cryptodome and erupt.
Those who were in the area had nowhere to take refuge.
The volcano exploded on its side and caused a massive landslide of a superheated mixture of ash, rock fragments and gas that flowed downhill.
Ash and gas then rose and blocked out the sun, completely darkening the sky.