CIOReview
CIOREVIEW >> Big Data >>

NOAA Announces Crowdsourcing Challenge to Mitigate Effect of Geomagnetic Storms on Navigation Systems

By CIOReview | Tuesday, January 5, 2021

The challenge set by DrivenData and HeroX aims to mitigate the effect of geomagnetic storms on navigation systems by improving forecasting by increasing the precision of real-time magnetic storms.

FREMONT, CA: In collaboration with the NASA Tournament Lab, the National Oceanic and Atmospheric Administration (NOAA) announced its "MagNet: Model Geomagnetic Field" crowdsourcing challenge. The challenge set by DrivenData and HeroX aims to mitigate the effect of geomagnetic storms on navigation systems by improving forecasting by increasing the precision of real-time magnetic storms.

"As we enter the next solar cycle and the navigation technologies we rely on everyday are always advancing, it is all the more important that we are prepared and deploying the most updated environmental information services possible," said Rob Redmon, a space scientist and the lead of the NCEI Solar & Terrestrial Physics Section, NOAA National Centers for Environmental Information (NCEI), which partners with the Cooperative Institute for Research in Environmental Sciences (CIRES) to develop magnetic modeling knowledge and applications. "This is an area where we need input and insight from the crowd."

NOAA is calling on the global group of problem solvers and computer scientists to develop improved models to predict shifts in Earth's magnetic field. The transition of energy from the solar wind to the Earth's magnetic field induces geomagnetic storms. The subsequent changes in the magnetic field raise the errors of magnetic navigation.

"We look forward to hearing from our network of problem solvers because this is something, we all have a stake in," said Christian Cotichini, CEO, HeroX. "Better understanding geomagnetic storms means we can better respond to them, and protect our technology systems against serious events."

Over the past thirty years, models have been proposed for modeling solar winds and magnetic field fluctuations, including mathematical, physical, and machine learning methods. While machine learning models typically work better than models based on other ways, there is still much room for improvement, particularly when forecasting extreme events. More specifically, the organization is searching for technologies that operate on raw, real-time data sources and are agnostic for sensor malfunctions and noise.

"This is a hard problem where many different approaches may prove useful. A machine learning challenge enables thousands of data experts to bring their diverse backgrounds, skills, and ideas to produce the best results for magnetic field monitoring," said Greg Lipstein, CEO and Co-Founder, DrivenData.

The objective of this challenge is to build models for forecasting variations in the magnetic field that:

1. Push the boundaries of predictive efficiency,

2. Do so under operationally viable constraints, and

3. Use defined real-time solar-wind data feeds.

The institution will publish both award-winning solutions under an open-source license for continuing community use and learning.

GPS provides precise coordinates for the point but does not offer instructions to the end. Therefore, the absolute directional information provided by the Earth's magnetic field is of primary importance for navigation and systems used by aircraft, vehicles, antennas, satellites, directional drilling, and smartphones. NCEI and CIRES design magnetic field reference models to assist navigation and scientific study.

"Since geomagnetic storms increase the pointing error, the accuracy of the magnetic disturbance forecasting is critically important for our operational magnetic reference models," said Manoj Nair, a research scientist with the CIRES/NCEI geomagnetism team.