SkyServe tests AI models with JPL and D-Orbit

SAN FRANCISCO – Indian edge computing startup SkyServe is working with NASA’s Jet Propulsion Laboratory to test artificial intelligence models on a D-Orbit satellite.

The models, developed as part of NASA’s New Observations Strategies Sensorweb, are designed for near-real-time monitoring of wildfires, floods, urban heat islands and other phenomena for scientific research and disaster monitoring.

In March, SkyServe completed testing of JPL’s AI models on its STORM edge-computing suite installed on a D-Orbit ION Satellite Carrier in low-Earth orbit.

“We deployed this software onboard the existing satellite and completed the mission,” Vinay Simha, SkyServe founder and CEO, told SpaceNews. “We uplinked it from the ground station and ran these AI models onboard. It’s a new way of Earth observation.”

The models focused on preprocessing and optimizing water and vegetation observations to make them easier to download. “Achieving these objectives requires sophisticated edge computing technology to integrate and optimize AI models across diverse sensor configurations,” according to the news release.

“SkyServe’s technology plays a pivotal role in streamlining AI model deployment across diverse satellite platforms, ensuring consistency and efficiency,” Vishesh Vatsal, SkyServe chief technology officer, said in a statement. “Our platform bridges the gap between groundbreaking AI models and the hardware diversity of satellite systems, enabling a unified approach to Earth observation.

D-Orbit announced plans in 2024 to equip ION satellite carriers with SkyServe STORM. Similarly, Loft Orbital installed the SkyServe edge computer on its spacecraft.  Another SkyServe STORM is a hosted payload on a SatRevolution cubesat launched in December on India’s Polar Satellite Launch Vehicle.

In addition to STORM, SkyServe offers Surge, a platform for developing and testing AI models on the ground.

Related