NASA uses AI to predict solar storms, and the earth can respond to crises half an hour in advance

NASA researchers used artificial intelligence (AI) models to analyze solar storm data to develop an early warning system that could give Earth about 30 minutes before a solar storm has a potentially catastrophic impact on the planet. warning time.

Solar storms are violent explosions that occur on the surface of the sun, ejecting large amounts of high-energy particles and plasma into space. These materials travel slower than light, so when they approach the Earth, they can be detected in advance through radio signals. The main harm caused by solar storms to the earth is to interfere with or damage power and communication facilities. For example, a solar storm 35 years ago caused a power outage in Quebec for several hours. If a more extreme solar storm occurred, such as the Carrington event more than 150 years ago, today's power and communications infrastructure would suffer massive damage.

Scientists have been paying attention to this issue, and there are currently many satellites observing the sun that can be used to identify these solar storms. These satellites include ACE, Wind, IMP-8 and Geotail, which provide data to the NASA team.

It’s not enough to know that a solar storm is coming; you must also know what impact it will have on Earth when it reaches Earth. Therefore, the researchers also collected data from ground-based sites that were also affected by some of the storms detected by the satellite.

The scientists then began training a deep learning model, which they named DAGGER, most notably for its improved speed compared to existing predictive algorithms trying to do the same thing. Researchers led by Vishal Upendran 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 one prediction can be made every minute. Earlier algorithms took much longer, almost to the point where there was almost no warning time before a solar storm hit Earth.

This solar storm warning system’s combination of predictive speed and capability makes DAGGER a major advance in predicting and accurately responding to the potential dangers of solar storms. IT House noted that the system has been released on an open source platform to collect large amounts of data before the sun reaches the peak of its 11-year solar activity cycle (expected in 2025). This gives utilities and communications companies several years to integrate DAGGER into their threat assessment systems to prepare before the worst solar storms arrive.

The above is the detailed content of NASA uses AI to predict solar storms, and the earth can respond to crises half an hour in advance. For more information, please follow other related articles on the PHP Chinese website!