NASA: We had a 30-minute warning before a deadly solar storm hit Earth

We’ve touched on the dangers of solar storms many times in the past. We’ve also recently started reporting more stories involving some form of AI, especially in the past few months as it has come back to the fore in many discussions of the technologies.

So it should come as no surprise that a team at NASA has been busy applying artificial intelligence models to solar storm data to develop an early warning system that it believes can give the planet about 30 minutes notice before a devastating solar storm hits a certain area.

This lag is thanks to the fact that light (i.e. the radio signals that make them up) can travel faster than solar matter emitted by the sun if these solar storms occur. In some events, like the one that affected Quebec some 35 years ago, they can cut out power for hours.

More extreme events, like the Carrington event that happened more than 150 years ago, could cause massive damage to electrical and communications infrastructure if they happened that day.

Scientists have long been aware of the problem and did not sit idly by. At this point in our species’ exploration of the solar system, plenty of satellites are looking at the sun that can be used to identify these solar eruptions.

border frame=”0″allow=”accelerometer; auto start; Clipboard write. gyroscope encoded media; picture in picture; web sharing “allowfullscreen>”.

Some of these satellites include ACE, Wind, IMP-8 and Geotail, which provided the NASA team with data. But, as any AI researcher can tell you, in order to develop a predictive model, you need to tell it what the prediction is meant to be.

Knowing that a solar storm is on its way is only one part of the battle – you also have to know what kind of impact it will have on Earth when it strikes there. So the researchers also collected data from surface stations that were also affected by some of the satellite-observed storms.

The scientists then set about training a deep learning model, which has recently become almost a household word. In this case, they called it DAGGER, and it has some pretty impressive specs compared to existing predictive algorithms that have tried to do the same thing.

Most notably the speed increase. The researchers, led by Vishal Abhindran of the Inter-University Center for Astronomy and Astrophysics in India, claim that the algorithm can predict the severity and direction of a solar storm event in less than a second and is capable of forecasting every minute. .

Previous attempts by previous algorithms would have taken much longer — almost to the point that they would give no warning time before the storm hits the ground.

Part of this struggle with punctuality was because it was mathematically difficult to calculate where in the world a storm might hit. This is another step forward for DAGGER, which can implement its rapid prediction logic for the entire surface area of ​​the Earth.

Making such predictions locally is very important – any time a solar storm might hit Earth, half of the globe would be shielded by the entire size of the planet – in what we usually refer to as “nighttime”.

This combined speed of forecasting with the ability to apply those predictions to the entire globe makes DAGGER a huge step forward in accurately predicting and responding to potential hazards from solar storms. And it’s launching on an open-source platform just in time to collect plenty of data as the sun reaches the peak of its 11-year solar cycle in 2025.

That gives utility and telecoms companies a few years to incorporate DAGGER into their threat assessment systems before more severe weather hits.

While there may not be any tornado-like sirens, which we have here in the Midwestern United States, at least the right people will be made aware of the danger faster than they have before.

This article was originally published by Universe Today. Read the original article.

#NASA #30minute #warning #deadly #solar #storm #hit #Earth

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top