Whakaari/White Island. Photo credit: Wikimedia Commons
Scientists in New Zealand have developed a volcano eruption early-warning system that they believe could have saved the lives of the 21 people killed in the Whakaari/White Island eruption late last year.
They say their system uses sophisticated machine learning algorithms to analyse data patterns occurring in known volcanic danger areas and ‘learn’ from them in order to predict when an eruption is about to happen.
In the case of the Whakaari/White Island eruption, which also injured 26 people, the technology could have given up to 16 hours’ prior warning, they claim.
According to a report in the New Zealand Herald newspaper, the country doesn’t currently have an advanced real-time warning system for volcanic eruptions.
Instead, the existing Volcano Alert Level (VAL) system is updated every few weeks or months and relies on human judgement and consensus amongst scientists to spot activity that could signal a pending eruption.
The VAL system only flagged a critical Level Three warning for the December eruption after it had already occurred.
“That eruption was preceded by a strong burst of seismic energy 17 hours earlier, a sure sign that fresh magmatic fluid was rising up and pressurising water trapped in the rock,” the developer and engineer of the new system, Dr David Dempsey from the University of Auckland, told the New Zealand Herald.
“The resulting explosion was like a pressure cooker blasting its lid off, and that early seismic burst is the most common indication of imminent eruption at Whakaari.
“It’s a warning sign that could have been detected almost instantly by the forecasting system we have developed,” Dempsey said.
Dempsey is one of three academics from the university who have developed the new system with funding from the Ministry of Business, Innovation and Employment.
The other two are Dr Andreas Kempa-Liehr from the Faculty of Engineering, and Professor Shane Cronin from the Faculty of Science.