UFO Hunters Built an Open-Source AI System To Scan The Skies

Last year, the Pentagon began releasing regular reports on UFO sightings after the U.S. government established an office dedicated to tracking the aerial anomalies—which it calls unidentified aerial phenomena, or UAPs—for the first time. But ever since the Roswell “flying saucer” crash of 1947, officials have frustrated veteran UFO hunters, often dismissing the mysterious objects as “swamp gas,” “weather balloons,” or, more recently, “sky trash.”

Now, frustrated with a lack of transparency and trust around official accounts of UFO phenomena, a team of developers has decided to take matters into their own hands with an open source citizen science project called Sky360, which aims to blanket the earth in affordable monitoring stations to watch the skies 24/7, and even plans to use AI and machine learning to spot anomalous behavior.

Interest in UFOs has waxed and waned over the years, but with the Pentagon’s recent declassification of the “Tic Tac” videos in 2020—an unprecedented acknowledgment of mysterious aerial phenomena from official sources—the frenzy was well and truly reignited.

Confirmation of inexplicable flying Tic Tacs or not, that overarching air of secrecy has never really gone away. Although the Director of National Intelligence now discloses UAP sightings, many of those remain unsolved, and the US Navy has said that releasing more videos would be a national security risk.

Unlike earlier 20th century efforts such as inventors proposing “geomagnetic detectors” to discover nearby UFOs, or more recent software like the short-lived UFO ID project, Sky360 hopes that it can establish a network of autonomously operating surveillance units to gather real-time data of our skies.

Citizen-led UFO research is not new. Organizations like MUFON, founded in 1969, have long investigated sightings, while amateur groups like the American Flying Saucer Investigating Committee of Columbus even ran statistical analysis on sightings in the 1960s (finding that most of them happened on Wednesdays). However, Sky360 believes that the level of interest and the technology have now both reached an inflection point, where citizen researchers can actually generate large-scale actionable data for analysis all on their own.

“There's distrust [about how governments managed UAP sightings] and that's why the idea of a citizen science formation, to take this into our own hands, and to create our own information about it [is necessary],” Sky360 co-chair Richard G Hopf told Motherboard. “Most data is from military-use sensors, like the National Reconnaissance Office. They have a lot of data, but they would never make it public nor would they give it to universities for analysis.”

The Sky360 stations consist of an AllSkyCam with a wide angle fish-eye lens and a pan-tilt-focus camera, with the fish-eye camera registering all movement. Underlying software performs an initial rough analysis of these events, and decides whether to activate other sensors—and if so, the pan-tilt-focus camera zooms in on the object, tracks it, and further analyzes it.

According to developer Nikola Galiot, the software is currently based on a computer vision “background subtraction” algorithm that detects any motion in the frame compared to previous frames captured; anything that moves is then tracked as long as possible and then automatically classified. The idea is that the more data these monitoring stations acquire, the better the classification will be. There are a combination of AI models under the hood, and the system is built using the open-source TensorFlow machine learning platform so it can be deployed on almost any computer. Next, the all-volunteer team wants to create a single algorithm capable of detection, tracking and classification all in one.

All the hardware components, from the cameras to passive radar and temperature gauges, can be bought cheaply and off-the-shelf worldwide—with the ultimate goal of finding the most effective combinations for the lowest price. Schematics, blueprints, and suggested equipment are all available on the Sky360 site and interested parties are encouraged to join the project’s Discord server. There are currently 20 stations set up across the world, from the USA to Canada to more remote regions like the Azores in the middle of the Atlantic.

While groups like SETI look for signals of alien intelligence farther away than our planet, very few are searching for signs within our atmosphere, Hopf says. Those that are looking closer to home—such as when the Main Astronomical Observatory of the National Academy of Sciences (NAS) in Ukraine said they spotted UFOs over Kyiv “all the time”—tend to be isolated and working alone. What’s missing, suggests Hopf, is generating data at scale and joining it all together.

Open source software, where source code is available free to everyone, not only forms the backbone of the internet itself, but has long been essential to huge institutions in the science world—whether open hardware standards from CERN, which hosts the Large Hadron Collider, or the Institute Laue-Langevin center for neutron science research, which contributes to, and runs largely on, open source. But more recently, open source models have benefited citizen science initiatives too, which were once relegated to the fringe, by making tooling accessible to the wider population and at a relatively low cost.

“Anytime you give more opportunities to discover to the general population, the more options you have for innovation and growth,” Sarah Polan, field CTO of open source company HashiCorp told Motherboard at the recent KubeCon event. “Opening that up to open source hardware or software, or going down the AI route, is powerful for aggregating and managing all of that data. It's really powerful to give that to a population, whether that's looking for things like UFOs, or as I've seen done across Africa, to open source cell phones to bring internet to the bush—it’s just incredibly powerful across the board.”

Once enough of the Sky360 stations have been deployed, the next step is to work towards real-time monitoring, drawing all the data together, and analyzing it. By striving to create a huge, open, transparent network, anyone would be free to examine the data themselves.

In June of this year, Sky360, which has a team of 30 volunteer developers working on the software, hopes to release its first developer-oriented open source build. At its heart is a component called ‘SimpleTracker’, which receives images frame by frame from the cameras, auto-adjusting parameters to get the best picture possible. The component determines whether something in the frame is moving, and if so, another analysis is performed, where a machine learning algorithm trained on the trajectories of normal flying objects like planes, birds, or insects, attempts to classify the object based on its movement. If it seems anomalous, it’s flagged for further investigation.

Obviously, a grassroots surveillance network distributed across the globe could prove bothersome for nations and militaries that are used to operating in relative secrecy. According to Hopf, the founders of a predecessor project, SkyHub, had ties to US intelligence, and decided to wind it down with no explanation.

“Three Americans started SkyHub three years ago, I was number five in the team, and then two years ago, the Americans decided to shut it down,” Hopf says. “The reason why they shut it down was very dubious to me: they didn't tell us Europeans anything about what was going down. It was fishy.”

Hopf decided to relocate to Europe and decentralize the whole project to protect it. Similarly, Nikola Galiot is distributing the data in a peer-to-peer way to build in redundancy, and is exploring more cryptographically secure infrastructure like Tor, the Invisible Internet Project, or IPFS. “It's really hard to get rid of it once it is deployed and distributed to the world,” Galiot said.

Whether these efforts find anything truly unusual or not is anyone's guess, but if Sky360 is successful, perhaps we'll no longer simply 'want to believe' - we'll be able to see for ourselves.