AI improves the prediction of solar storms


The space weather not only provides impressive plays of light but also known as auroras but can also have a considerable influence on our modern technologies. So-called geomagnetic storms can, for example, significantly affect the power supply, GPS systems, and other communication systems on which our modern society depends. An expansion of our space programs and the increasing human presence in space, such as on the International Space Station or soon again on the Moon, requires an accurate prediction of the solar wind. The solar wind is a stream of charged particles that spreads into space from our central star and also meets the Earth's magnetic field. Physical Models and Artificial Intelligence

Predicting such solar storms poses an unsolved problem even for the most advanced physical models.

In a wide variety of areas such as finance, logistics, or classical meteorology, enormous progress is currently being made with artificial intelligence methods when it comes to predicting future developments. An application to the solar wind is therefore obvious, even if space probes generate significantly fewer data overall than in the other areas mentioned.
In the new study, researchers from ZAMG and IWF Graz, in cooperation with the US Air Force Research Lab and NASA Goddard, were looking for a new approach to improve
prediction. "We have succeeded in combining models of the Sun's magnetic field with algorithms from the field of machine learning to predict the effects of the solar wind on the Earth much better than was previously possible," explains ZAMG researcher Rachel Bailey, first author of the study. Improvement of the forecast by 20 percent "We had to study 25 years of measurements and model data.

But the results more than prove this effort right," Bailey continues. The new method reduces the error in the speed of the solar wind from 99 kilometers per second to 78 kilometers per second, improving the forecast in general by about 20 percent. "The new approach paves the way for optimizing more complex simulations of the solar wind in real-time in the future," adds IMF researcher and model developer Martin Reiss.
The research project is led by the IMF and is funded by the FWF.

Further information Study: -> Link to the study Related messages at

Join the discussion in the Raumcon forum:

Post a Comment