It uses artificial intelligence to predict space

A Northumbria University physicist has been awarded more than half a million pounds to develop artificial intelligence that will protect Earth from devastating space storms.

Activity from the Sun such as solar flares, known as a coronal mass ejection, shoots plasma toward Earth at supersonic speeds, which can seriously disrupt power and communications systems.

With our increasing reliance on technology, solar storms pose a serious threat to our daily lives, leading to severe space weather being added to the UK’s National Risk Assessment for the first time in 2011.

Northumbria Dr. Andy Smith He was recently awarded a research fellowship from Natural Environment Research Council (NERC) To explore how machine learning, inspired by physics, can be used to more accurately predict space weather and forecast dangerous space storms.

during the Next generation, physics-inspired AI for space weather forecasting Dr. Smith and his team will analyze massive amounts of data from satellites and space missions over the past 20 years to gain a better understanding of the conditions under which storms are likely to occur.

They will then develop sophisticated computer models that will use the data collected to predict when such storms will occur in the future, and predict phenomena such as the northern lights or the aurora borealis.

As Dr Smith explains: “One of the primary ways that space weather can affect society is through an unexpected surge of energy in power grids and pipelines on Earth.

“These surges can accelerate the aging of power systems, or even lead to immediate failure of components such as power transformers, resulting in a complete loss of power.

“This research will take a leap forward in understanding and predicting when we are at risk of experiencing these surges caused by rapid changes in the Earth’s magnetic field.”

Throughout history, there have been many examples of dangerous geomagnetic space storms. In March 1989, Quebec City, Canada, lost power for more than nine hours in the aftermath of a massive solar storm that produced the aurora borealis, or “polar lights,” as far south as Texas and Florida.

And in 2003, Halloween solar storms, named because they occurred at the end of October, affected satellite systems and communications, with aircraft advised to avoid high altitudes near the polar regions, and one-hour power outages in Sweden.

But the deadliest geomagnetic storm ever recorded was the 1859 Carrington event, which led to powerful auroral displays visible around the world, as well as fires at multiple telegraph stations. The solar flare associated with the event was observed and recorded independently by British astronomers Richard Christopher Carrington and Richard Hodgson.

As Dr Smith explains: “Our reliance on electrical power grids means that a storm on the same scale as the Carrington event will have severe consequences today, making an accurate forecast system all the more important.

“The technology we develop through this project can protect the earth from the impact of geomagnetic storms and we can also predict the occurrence of such events, which allows us to prepare.

“For example, in the UK, this will be coordinated by the Met Office who will inform the national grid, which in turn will activate plans to protect our power grid.

“It’s not a case of if Earth will be hit by a dangerous space weather event, it’s a case of when – and an AI system inspired by physics will allow us to predict such an event and protect ourselves from it.”

Dr. Smith is a member of the Northumbria University Heliospheric and Space Physics Research GroupThis is the latest in a series of high-profile grants awarded to academics at the university who study the impact of space weather on Earth.

In 2021, a team led by Professor Claire Watt has secured £400,000 from the Science and Technology Facilities Council (STFC) to develop New methods for predicting conditions in the radiation belts above Earthproviding safer conditions for satellites and spacecraft.

Northumbria’s participation was led by Dr Sean Bloomfield Space Weather Experimental Package (SWEEP) projectCommissioned by the Met Office to develop an improved system for forecasting solar storms. He was also a Project Scientist on the EC Horizon 2020 Funding FLARECAST projectwhich involved scientists from six countries developing a service to predict the occurrence of solar flares.

Leading by Dr Richard Morton is £1.2m The Solar Alfvenic Wave Pattern Detection (RiPSAW) Projecthaving been awarded the prestigious UKRI Future Pioneers Fellowship in 2020. The project involves the use of advanced mathematical techniques and sophisticated computer simulations to create models of the Sun that provide new insight into the physics behind its activity.

Professor James McLaughlin He leads the Heliophysics and Space Research Group at Northumbria University and is the Principal Investigator at £1.3m NUdata STFC Doctoral Training Center in Data Science Intensive.

He said: “Northumbria University plays multiple key roles in the UK’s quest to understand the scientific and technical aspects of space weather. Through its Data Science-Intensive PhD Training Centre, Northumbria is training the next generation of data science and AI professionals. Dr Smith’s new project complements and enhances both These are the university’s areas of strength.”

Find out more about Northumbria BSc in Astrophysics degreewhich includes learning about space weather, artificial intelligence, and the latest astrophysics research.