As part of its effort to expand its focus into space, Microsoft has developed an on-orbit computing platform to run spacecraft with AI (opens in new tab) Workloads can be connected to hyperscale Azure (opens in new tab) Cloud.
In the first of a series of space-related partnerships, the software giant is working with Thales Alenia Space to demonstrate and validate computing technologies in orbit with a demonstration aboard the International Space Station (opens in new tab). Together, the two companies will deploy a powerful on-orbit computer, an on-orbit application framework and high-performance Earth observation sensors to develop new on-orbit climate data processing applications to benefit Earth’s sustainability.
Microsoft is also collaborating with Loft Orbital to enable a new way to develop, test and validate software applications for space systems on Microsoft Azure. These applications are then seamlessly deployed to orbiting satellites using Loft Orbital’s space infrastructure tools and platforms.
Finally, Microsoft is working with Ball Aerospace to develop a series of orbit testbed satellites that will be used to implement new software and hardware for the US government. Both companies will collaborate in conducting these spacecraft missions to demonstrate on-orbit reconfigurable processing technologies leveraging the Azure cloud.
Combining AI and satellite imagery
Satellite imagery is already a valuable asset, but when used with geospatial AI, analysts can monitor the detection of changes for their respective areas of interest.
This is particularly useful for industries that monitor, measure and/or monetize large areas of the earth. However, satellite imagery consists of unstructured big data (opens in new tab) which requires significant resources for transformation and analysis to access and store information and use it as structured data.
To accomplish this task, the Azure Space (opens in new tab) team has released a new reference architecture that demonstrates how to apply AI to satellite imagery at scale using Azure resources. Because Azure offers orchestration flexibility, customers can bring their own images, but they can also call another image provider API.
When it comes to geospatial and remote-sensing AI, Microsoft already has partnerships with Blackshark.ai, Orbital Insight, and Esri, while customers looking to develop AI can leverage the company’s tools, including Azure Machine Learning (opens in new tab) and Azure CustomVision.
We’ll likely hear more from the Azure Space team about their latest endeavors in space once their on-orbit computing projects enter testing.