Using AI to Predict the Danger of Solar Storms for Earth
February 15, 2022

Using AI to Predict the Danger of Solar Storms for Earth

This press release has been translated from the original German version by the Know-Center.

Researchers from the Know-Center and the Space Research Institute are developing a prediction tool, funded through Europlanet 2024 RI, that determines the strength of solar storms. Better forecasts could prevent a blackout from a massive solar storm.

While there is a current focus on the energy crisis in Europe, less attention is paid to the danger threatening from space. Solar storms are usually so weak that the atmosphere and the earth’s magnetic field protect the planet sufficiently from them. However, according to experts, a solar storm could hit us at any time and have serious effects on power grids, radio networks and satellites.

Around ten percent of all satellites could fail during such an event, and this would cause problems in areas where precise positioning is required, such as shipping and air traffic. Widespread power outages due to increased transformer voltages and damage to undersea cables, leading to nationwide internet outages, are also conceivable.

Space weather researchers can observe whether a solar storm is heading towards Earth, but it is difficult to estimate how massive the storm will be once it hits Earth. Now, data experts from the Know-Center and the Institute for Space Research, funded by the Europlanet 2024 Research Infrastructure (RI), have developed a prediction tool, based on Artificial Intelligence (AI), to better-estimate the strength of solar storms. The results were recently published as part of a study in the peer-reviewed journal, Space Weather.

Magnetic field determines the strength of solar storms

Solar activity fluctuates every eleven years between quiet and active phases. We are currently in an active phase, the maximum of which is expected in 2025. A geomagnetic storm occurs when solar storms interact with Earth’s magnetic field. In extreme cases, solar storms can reach Earth in less than a day. The ability of solar storms to cause extreme geomagnetic storms depends largely on the orientation of their magnetic field, known in technical jargon as the Bz magnetic field component. The relative orientation of this magnetic field component to the Earth’s magnetic field determines how much energy is transferred to Earth’s magnetic field. The larger a southward Bz component  is, the greater the risk of a massive geomagnetic storm. To date, however, the Bz magnetic field component cannot be predicted with sufficient advance warning before the solar storm hits Earth.

Machine learning provides better forecasting

‘It only takes a few minutes for data measured by spacecraft directly in the solar wind to be transmitted to Earth. We first looked at whether information about the first few hours of a solar storm is sufficient to be able to predict its strength,’ explains Hannah Rüdisser from Know-Center.

Using Machine Learning (ML), the researchers developed a program to predict the Bz magnetic field component. The program was trained and tested with data from 348 different solar storms collected by the Wind, STEREO-A and STEREO-B spacecraft since 2007. To test the prediction tool in a real-time experimental mode, the team simulates how solar storms are measured by spacecraft and evaluates how the continuous feeding of new information improves the predictions.

‘Our forecasting tool can predict the Bz component quite well. It works particularly well when we use data from the first four hours of the solar storm’s magnetic  flux rope. New space missions will provide us with even more data in the coming years, further increasing the accuracy of the predictions. Our approach could thus lead to an improved space weather forecast and in the event of a massive solar storm, affected areas could be warned at an early stage and major damage prevented,’ says Rüdisser.

In the next step, the researchers want to use AI methods to automatically detect solar storms in the solar wind. This automation is necessary to be able to use the Bz prediction method in real-time without a human expert having to continuously identify the solar storms.

Innovation for space exploration

The use of AI to analyze and classify planetary data sets is still relatively new, but is becoming increasingly important. ML enables algorithms to be trained to analyze huge amounts of data and derive predictions and new solutions from them. Potential applications of ML in planetary science have exploded over the past decade, but tools tailored to this area of research are still rare.

‘The Europlanet 2024 Research Infrastructure houses a large treasure trove of data that comes from space missions, simulations and laboratory experiments. Our goal is to extract the knowledge contained in this data and make it usable. For this we want to develop a series of ML tools that support researchers in planetary sciences in their work. This allows us to promote a broader use of ML technologies in data-driven space research,’ says Rüdisser.

More information

Machine Learning for Predicting the Bz Magnetic Field Component From Upstream in Situ Observations of Solar Coronal Mass Ejections‘, M. A. Reiss, C. Möstl, R. L. Bailey, H. T. Rüdisser, U. V. Amerstorfer, T. Amerstorfer, A. J. Weiss, J. Hinterreiter, A. Windisch. Space Weather, Volume 19, Issue 12.

About the Know Center

Know-Center is one of the leading European research centers for data-driven business and AI. Since 2001, well-known companies have been supported in using data as a success factor for their company. As an integral part of the European research landscape, the center successfully handles numerous projects and contract research at EU and national level. The K1 Competence Center, which is funded as part of COMET, is the leading training center for data scientists in Austria and also offers a range of Al training courses and advice for companies. The majority shareholder of the Know-Center is the Graz University of Technology, a major sponsor of local AI research, whose institutes carry out numerous projects together with the Know-Center. In 2020, Know-Center was the only Austrian center to receive the iSpace Gold Award from the Big Data Value Association, which was only given nine times in the entire EU.