Elon Musk and other AI leaders have repeatedly insisted that the solution to the industry’s extremely costly and energy-intensive data centers is to launch them into space, taking advantage of unfettered access to solar energy and virtually limitless real estate.
Late last month, SpaceX — now merged with xAI — filed a patent for an orbital data center constellation with the Federal Communications Commission. The idea is to have up to one million satellites circle the Earth at altitudes between 310 and 1,200 miles at a Sun-synchronous orbit to maximize the amount of solar energy captured.
The application didn’t elaborate on any of the specifics, suggesting SpaceX had only begun to ponder the idea. That’s despite Musk promising that space-based data centers could overtake their Earthbound counterparts as the most affordable way to power AI within just three years — likely yet another one of his characteristically overambitious timelines.
Many experts remain highly skeptical, questioning the financial feasibility and the technological limitations of running data centers in space.
And as Rebekah Reed — former NASA associate director and Harvard University associate director of the Program on Emerging Technology, Scientific Advancement, and Global Policy — argued in an essay for the Financial Times, it may be an even more cursed idea than we initially thought, pointing out considerable environmental concerns, on top of glaring questions regarding costs and operations.
“Treating orbit as a workaround for AI’s current energy-hungry training needs is, as OpenAI co-founder Sam Altman recently put it, ‘ridiculous,'” she wrote. “Orbital data centers are many years, perhaps decades, away.”
While Google CEO Sundar Pichai has predicted we’re only a decade away from orbital data centers, Altman ridiculed the idea, arguing during a recent conference that we’re simply “not there yet.”
Reed made the case that launching all of that mass into orbit would be prohibitively expensive. To become “economically viable”would require costs to fall below $200 per kilogram, a “sevenfold reduction from current levels.”
“That threshold isn’t expected until the mid-2030s,” she wrote.
Then there’s the issue of maintenance. In case a chip were to malfunction — or inevitably become obsolete — there’s a simple fix like sending an IT technician to rectify the issue.
“In orbit, that task requires either sophisticated in-space servicing or acceptance of degrading performance and stranded capital that becomes orbital debris as components age and fail,” Reed wrote.
Worse yet, falling satellites could inject harmful pollutants, including metals, into the upper atmosphere, an environmental toll scientists are still racing to understand.
Reed pointed to recent findings by researchers at Saarland University, Germany, who found that the carbon footprint of space data centers could exceed that of terrestrial data centers when taking manufacturing, launch, and disposal into consideration.
“Results show that, even under optimistic assumptions, in-orbit systems incur significantly higher carbon costs — up to an order of magnitude more than terrestrial equivalents — primarily due to embodied emissions from launch and re-entry,” they wrote in a yet-to-be-peer-reviewed paper last year.
Finally, an enormous orbital data center constellation of thousands of satellites could further clutter the Earth’s orbit, raising the “risk of collisions and debris, threatening communications, weather and navigation services,” Reed concluded. “Scaling data centers to match terrestrial demand would accelerate congestion and degrade the night sky.”
More on orbital data centers: Erratic Elon Musk Tells Employees to Build Massive Catapult on Moon