Satellites Interfere with Astronomical Data — Can AI Provide a Solution?

Satellites Interfere with Astronomical Data — Can AI Provide a Solution?

Astronomers have developed a machine learning algorithm that can detect satellite tracks in images of the night sky with high accuracy. This model makes data interpretation easier and could allow the removal of the fringes that are increasingly causing problems in astronomy.

Technology will be the problem “Photobombs” from Internet communications satellites cannot solve, but could help reduce their impact on some telescope images. Researchers touted the work at the International Astronomical Union (IAU) general meeting in Cape Town last month.

“Machine learning and artificial intelligence can help because if you have enough data, you can classify, okay, this is what a satellite looks like,” says Siegfried Eggl, an astrophysicist at the University of Illinois Urbana-Champaign. But the number of satellite launches and developments is happening at a "breakfast pace," he adds, and researchers are "doing their best to catch up."

Growing threat

Over the past five years, companies such as SpaceX in Hawthorne, California, Eutelsat OneWeb in London and Amazon's Project Kuiper in Redmond, Washington, have launched thousands of communications satellites into low Earth orbit. Many more are planned, including a 12,000-satellite mega-constellation called G60 Starlink to be launched by Shanghai Spacecom Satellite Technology in China. “There are now about a million satellites on the register of ambitions for the future,” said Richard Green, director of the IAU Center for Protecting Dark and Quiet Skies from Satellite Constellation Interference, during a session at the IAU General Assembly.

These satellites provide fast broadband internet access to people worldwide, but are increasingly disruptive for astronomers — they appear as bright streaks in sky images and can influence observations across the entire electromagnetic spectrum. Sensitive telescopes with wide fields of view are particularly affected by this satellite contamination. For example, it is estimated that the upcoming Vera Rubin Telescope could see more than a third of its images compromised.

“Astronomy today is a science involving large amounts of data, and there is no human being who can look at all the images recorded every night and see the streaks,” says Eggl. “Machine learning can help here.”

To develop a program to identify satellite tracks in telescope images, María Romero-Colmenares, a data scientist at the University of Atacama in Chile, trained a supervised machine learning algorithm on tens of thousands of images taken by a network of telescopes in Chile, Spain, Mexico, Vietnam and South Korea. “We knew when and where [in the sky] to observe the satellite, and made one observation with a satellite and one without,” says Romero-Colmenares, producing an equal number of clear and contaminated images. When she and her colleagues applied the model to publicly available data from the WASP (Wide Angle Search for Planets) and Hungarian Automated Telescope Network projects, the algorithm was able to identify 96% of satellite tracks.

Detecting the streaks is an important step toward eliminating them from images and data, says Jeremy Tregloan-Reed, an astrophysicist at the University of Atacama who worked with Romero-Colmenares on the project. The next challenge will be to develop tools that can actually remove the satellite tracks while preserving the underlying data. This is only possible in cases where the satellite is not so bright that it saturates the pixels of an image and fades into surrounding pixels, says Tregloan-Reed. If an overflow occurs, the underlying data cannot be saved.

By the end of next year, researchers hope to develop an open-source app and program that will allow observatories and amateur astronomers to identify and clean up contaminated images and data. Such measures are most likely to be successful on small telescopes with low-sensitivity cameras.

Star-like lightning

Other forms of satellite contamination are proving even more difficult to manage. When solar panels and other flat surfaces on satellites capture the light, they produce lightning bolts short-lived astronomical transients similar, energy bursts that can last from milliseconds to years.

“Since these flashes are very short, sometimes up to a millisecond, the satellite movement during them is negligible and we get a perfectly star-like flash,” says Sergey Karpov, an astronomer at the Central European Institute of Cosmology and Fundamental Physics in Prague. There is "no real way to distinguish these flashes from the astrophysical transients we want to detect — short of comparing their location directly to catalogs of satellite orbits," he adds.

Electronic equipment in satellites can also emit unintentional radiation, disrupting observations of the Big Bang's afterglow, Eggl says. Astronomers hope that studying this radiation, known as cosmic microwave background radiation, Answer questions about the expansion of the universe becomes. SpaceX's next generation of satellites, which the company began launching last year, emit about 30 times more radiation than the previous generation. This type of radiation is unregulated and could endanger entire observation bands.

Eggl points out that AI tools can't really reconstruct lost data, and the problem will get worse as more satellites are launched. “If you paint white paint over the Mona Lisa, at some point there will be nothing you can do, even if you train a machine learning algorithm on all of da Vinci's works,” says Eggl. “You may be able to guess what the painting might look like, but they can never reconstruct the data you lose.”

1. Bassa, C.G. et al. Astron. Astrophys. 689, L10 (2024).

   Article
   Google Scholar

Download references