How cloud technology is supporting space missions

We all know about cloud computing helping businesses to reduce their costs of operations and increase their efficiency but cloud computing in space is new.

Sometime last year, Amazon Web Services (AWS) together with space logistics and transportation company D-Orbit announced a one-of-a-kind experiment in which they equipped an orbiting satellite with a suite of computing and machine learning (ML) software. The experiment lasting 10 months enabled the satellite to analyze spatial data in real time, filter out the noise, and only send the most useful images back to earth for storage and further analysis.

The machine learning model had been trained to recognize specific objects in the sky such as clouds and wildfire smoke as well as objects on Earth such as buildings and ships.

Speaking on the experiment, Clint Crosier, director of AWS’s aerospace and satellite business said it was a demonstration of how cloud technology could be applied to space missions.

“As we look at the new missions in space, we’re going to be able to go out and repair satellites and operate from space stations which we could never do before. We’re also going to do asteroid mining, and entertainment and tourism in space, which all require robotics, greater autonomy, more processing speed, and more bandwidth,” Crosier said.

“All the new missions emerging in space in the next 10 or 20 years are going to require the same cloud-based advanced technology, so it’s our goal at AWS to push that to wherever customers need it,” he added.

Another area in space that will be transformed by cloud computing according to experts is debris identification and management.

Space debris continues to be a major concern with some studies predicting that if nothing is done about it by 2050, astronauts will struggle to get out of low earth orbit. And while the ultimate solution is to find a way to clear the debris companies like LeoLabs are addressing the problem by developing technologies that predict potential collisions between space objects and satellites.

After moving their systems to the cloud the company reduced the time it takes to calculate the probability of a collision from 8 hours to 10 seconds.

“That’s real-time space traffic management and that’s what cloud and the advanced processing capabilities of AI and ML will bring to these problem sets,” Crosier said.