Advertisement

Nasa’s new AI gives ‘30 minutes of advance warning’ before killer solar superstorms strike Earth

Nasa’s new AI gives ‘30 minutes of advance warning’ before killer solar superstorms strike Earth

Nasa has built an artificial intelligence model to predict where on Earth an impending solar storm would strike, a new system that scientists said can provide “30 minutes of advance warning”.

The AI model analyses Nasa satellite data to raise the alarm on dangerous space weather, said researchers from the American space agency’s Goddard Space Center.

The warning may provide just enough time for countries to prevent severe impacts of these storms on power grids and other critical infrastructure, according to the new study published recently in the journal Space Weather.

Solar storms are caused when the Sun emits a burst of electrically charged plasma in what is called a coronal mass ejection.

These charged particles create so-called geomagnetic storms that may cause blackouts and technological malfunctions of instruments on Earth as they interfere with the protective magnetic field around the planet.

While these storms range from mild to extreme, their effects could become increasingly disruptive in a technologically dependent world.

For instance, a solar storm in 1989 caused blackouts across Quebec, Canada for 12 hours, plunging millions into the dark and closing schools and businesses.

Another popular solar superstorm event known as the Carrington Event sparked fires at early telegraph stations in 1859 that prevented messages from being sent.

Scientists warned that the risk of such a devastating solar storm is increasing as we approach the next “solar maximum” – a peak in the Sun’s 11-year activity cycle.

To prevent such a devastation, Nasa scientists developed the new AI model to identify links between solar wind measurements from previous Sun missions and geomagnetic disturbances observed at ground stations across Earth.

The computer model they developed, called DAGGER, can quickly and accurately predict geomagnetic disturbances worldwide, “30 minutes before they occur,” researchers said.

When they tested the model against two geomagnetic storms that happened in August 2011 and March 2015, it was able to “quickly and accurately” forecast the storm’s impacts around the world.

The new prediction system is the first to combine swift analysis of AI, with real measurements from space and across Earth to generate frequently updated predictions.

Scientists believe the early warning provided by the system can help take action to protect infrastructure from an impending solar storm, such as temporarily taking sensitive systems offline or moving satellites to different orbits.