Home Radiation Living on the Edge: Satellites Adopt Powerful Computers

Living on the Edge: Satellites Adopt Powerful Computers


The latest Apple Watch has 16 times the memory of NASA’s Mars 2020 rover’s central processor. For the new iPhone, 64 times the memory of the car-sized rover is standard.

For decades, people have dismissed comparisons between terrestrial and space-based processors by pointing out the extremes of radiation and temperature faced by space electronics. Only components custom-built for spaceflight and proven to work after many years in orbit have been deemed tough enough for multi-billion dollar space agency missions.

While this may still be the best bet for high-level space missions, spacecraft operating closer to Earth are adopting state-of-the-art onboard processors. Future missions will require even greater computing capacity.

Satellite sensors produce “an enormous amount of data in the form of scientific research, Earth observation, national security,” Naeem Altaf, IBM Distinguished Engineer and IBM Chief Technology Officer, said via email. Space Tech. “To extract value fast from data, we will need to bring computation closer to data.”

Consider Earth observation. Traditionally, electro-optical imagery and synthetic aperture radar data have been sent to the ground for processing. This is still largely the case, but new Earth observation sensors continue to increase the volume of data acquired in orbit, sometimes quite dramatically. At the same time, customers want quick access to insights from various datasets.

Weather observation is a good example. Numerical weather models merge vast amounts of data drawn for space, airborne, maritime and ground sensors. Although no one is proposing to run the forecasting algorithms on satellites, AAC Clyde Space, the Swedish company that provides the basic avionics for the European Space Agency’s Arctic weather satellite, sees improvements in onboard processing as a way speed up the delivery of meteorological data.

“We see an opportunity in the future to do a lot of onboard processing: prepare the data, compress it, and start merging the data,” said Luis Gomes, CEO of AAC Clyde Space. “Our goal is real-time weather observations from space. For this, we need to bundle the data effectively and efficiently to reduce the downlink time. »

Hyperspectral sensors also produce huge datasets that make on-board processing “pretty critical,” Gomes said.

Some of the new satellite computers will be dedicated to processing sensor data. Others will help spacecraft choreograph complex operations.

Future satellites will likely operate in swarms, communicating via inter-satellite links and working together to capture unique data sets and expand communication networks. Eventually, constellations will use artificial intelligence to fix problems, such as repairing or repositioning satellites based on onboard analysis of their health and performance, which will require extensive cutting-edge processing, a said Chuck Beames, president of the SmallSat Alliance, an industry association.


Edge processing, bringing computation closer to data sources, is increasingly popular on Earth. Oil and gas companies, for example, analyze data near sensors that monitor heavy equipment at remote sites to quickly identify equipment problems and reduce communication and data storage expenses.

Companies ranging from IBM and Hewlett Packard Enterprise to startups around the world are positioning themselves to meet what they see as an inevitable demand for improved, space-based advanced processing, starting with on-board satellites and expanding extending to data centers in Earth and Lunar orbit.

Artist’s impression of the Japanese asteroid mission Hayabusa-2 passing close to Earth. Israeli startup Ramon.Space provided computing technology for the Japanese Space Agency mission. 1 credit

Exodus Orbitals, a Canadian startup that leases satellite services to software application developers, created Edge Computing in Space Alliance in November. The organization quickly attracted nearly twenty members.

One of the members, Ramon.Space, advertises “space-resilient supercomputing systems”. While they bear little resemblance to Earth-based supercomputers, they’re very different from low-capacity spaceflight computers and “much closer to the kind of computing capability we have on Earth,” said Lisa Kuo, vice president of strategic sales. for Ramon.Space, an Israeli company created in 2004 which is expanding internationally. “We go through space computing systems with a very fine-toothed comb and adopt the optimal radiation hardening technique for each component.”

In contrast to the bespoke approach, Pasadena, Calif.-based startup Exo-Space offers FeatherEdge, a platform that applies artificial intelligence and machine learning to Earth observation data to quickly extract insights. precious.

In the long term, Exo-Space plans “to adapt the technology to more general use cases like constellation management or predictive maintenance,” said CEO Jeremy Allam.

Sydney-based Spiral Blue is also applying artificial intelligence to Earth imagery with its Space Edge computer.

“Satellites can capture far more data than they can produce,” said Taofiq Huq, Founder and CEO of Spiral Blue. With improved on-board processing, satellites can highlight and redirect the most important information, like ship locations for maritime vessel tracking, he added.


Other companies specialize in packaging terrestrial computers for spaceflight. OrbitsEdge, for example, works with customers including HPE to provide radiation shielding and thermal management systems that allow computers designed for terrestrial applications to operate in orbit.

“By leveraging the high-powered computing pipeline, we can ensure that everything we fly is the most modern,” said Rick Ward, CTO and founder of Titusville, Fla.-based OrbitsEdge. . “When we move into quantum computing, and we’ve already had conversations with some of the quantum computing companies, we can do that as well.”

Cosmic Shielding Corp. takes a similar approach but instead of focusing on protecting processors, the Atlanta startup developed a 3D-printed polymer to protect people and electronics in orbit.

“You can build a satellite bus out of this material, and it will bring significant improvements,” said Yanni Barghouty, founder and CEO of Cosmic Shielding. “Right now, we’re seeing about a 60-70% reduction in radiation dose rate compared to traditional materials.”


In addition to improving on-board processing, companies are installing edge processors in ground stations and are planning to launch dedicated data processing constellations.

“Edge computing can be performed across different segments, depending on the use case and the criticality of the data,” IBM’s Altaf said. “We can have dedicated compute satellites, which are responsible for supporting heavy payloads in orbit and performing compute services for other satellites.”

If history is any guide, the demand for in-orbit data processing will continue to climb. Successive generations of terrestrial applications invariably require additional memory and processing speed.

In space, like on the ground, “you want it to be faster, you want better networking, and you want more power,” said Mark Fernandez, HPE principal investigator for the Spaceborne Computer-2 on the Station. international space.

This article originally appeared in the January 2022 issue of SpaceNews magazine.