Deepfake AI, which enables the creation of produce startlingly realistic, computer-generated images and videos of human beings, has its issues.
But could deepfake technology have scientific uses? A group of solar scientists seem to think so, and they're using it to solve one of the biggest mysteries about our host star, the Sun.
You could be forgiven for thinking that the outer atmosphere of the Sun would be cooler than the layers closer to the surface.
But, it turns out, this is not the case. In fact, for decades, solar scientists have been trying to establish why the outer layers of the Sun are hotter that the inner layers, and deepfake AI could help solve the mystery.
New research on the subject, carried out by astronomers from Northumbria University and the University of Bern, is being presented at the National Astronomy Meeting this week, held at Cardiff University.
There are two main schools of thought regarding the apparently contradictory nature of the Sun's surface.
Could the hotter, outer layers be a result of heat generated via the dissipation of waves in solar plasma?
Or could it be a result of energetic reconnections of magnetic lines?
Solar scientists say there is evidence for both, but point to something called 'coronal rain', whereby loops of cooler plasma project outwards from the surface of the Sun and then fall back into the upper regions of its atmosphere.
If solar astronomers can calculate how much coronal rain falls back onto the Sun, they may be able to work out how the heating cycle works.
The issue is that the 'rain' needs to be observed separately from the other active features on the surface of the Sun which, especially as we are reaching the peak of the current solar cycle, is proving rather tricky.
The Atmospheric Imaging Assembly (AIA) instrument on NASA’s Solar Dynamics Observatory is responsible for a large proportion of data collected on coronal rain, but the rain is often obscured in images by hotter material.
Images captured by the Interface Region Imaging Spectrograph (IRIS), a NASA solar observation satellite, show the rain more clearly, but can only capture a limited field of view.
What's needed, is a set of data that combines the best bits of both.
Luke McMullan from Northumbria University has been teaching an AI machine learning algorithm to study IRIS images and enhance the AIA images, creating ‘deepfakes’ that enable solar astronomers to understand how much coronal rain falls in the Sun’s atmosphere.
This, it is hoped, could help solve the mystery of the Sun's unusual heat layering.
"We are living in a golden age for solar research," says Luke McMullan, the project’s lead researcher.
"Not only are we obtaining access to more high-resolution images of the solar atmosphere than ever before, but the rapid development and implementation of machine learning techniques in tandem with these observations allow us to find answers to problems that have hounded the community for decades.
"We anticipate this collaboration between observations and machine learning only to grow deeper and become a staple tool in our scientific arsenal."
