New satellite demonstrates the power of AI for Earth observation

Φsat-2, ESA’s groundbreaking cubesat designed to revolutionize Earth remark with synthetic intelligence, has launched.

The cubesat launched into its journey into space on 16 August at 20:56 CEST (11:56 native time) on board a SpaceX Falcon 9 rocket from the Vandenberg Area Drive Base in California, U.S., built-in by Exolaunch as a part of the Transporter-11 rideshare mission, which additionally included ESA’s Arctic Climate Satellite tv for pc.

At 21:50 CEST, Φsat-2 deployed from the launch vehicle and at 23:47 CEST the Svalbard floor station in Norway acquired the necessary sign indicating that Φsat-2 is now safely in orbit.

Φsat-2 will push the boundaries of Earth remark, demonstrating how AI applied sciences can be utilized to advance how we observe Earth from space. The miniature satellite is supplied with a state-of-the-art multispectral digicam and a strong AI laptop that analyzes and processes imagery whereas in orbit. It will show important for catastrophe response efforts, maritime monitoring, environmental safety and extra.

ESA’s Director of Earth Statement Packages, Simonetta Cheli, commented, “We’re thrilled in the present day to launch Φsat-2, which is able to display the transformative energy of synthetic intelligence in Earth remark. This mission heralds a brand new period of actionable insights from space, promising smarter and extra environment friendly methods of monitoring our planet.”

Nicola Melega, ESA’s Φsat-2 Technical Officer, added, “The Φsat-2 mission exhibits how superior AI know-how can remodel our capacity to observe and reply to modifications on Earth, making space information extra actionable and impactful than ever earlier than.”

A brand new period of synthetic intelligence

AI has considerably enhanced the way in which our planet is monitored and understood. AI capabilities enable for satellite data to be processed shortly and precisely—reworking huge quantities of uncooked information into actionable insights for scientists, companies and policymakers.

Whereas most AI processing happens on the bottom after the information has been downloaded, ESA’s Φsat-2 satellite will do that in real-time. As an alternative of downlinking giant quantities of uncooked information, together with these obscured by clouds, the onboard apps can course of these photos straight, making certain that solely essentially the most important info is shipped again to Earth. This innovation offers tangible advantages, enhances information transmission and accelerates resolution making.

Orbiting Earth at an altitude of 510 km, the satellite’s multispectral digicam photos Earth in seven completely different bands within the seen to near-infrared a part of the electromagnetic spectrum. The 6U Cubesat platform, designed and developed by OpenCosmos, runs AI apps that may be simply put in and operated remotely from Earth.

These apps can present actionable information for environmental protection and set a brand new normal in space-based AI know-how. At launch, Φsat-2 runs the next apps on board:

• Cloud detection.Not like conventional satellites that downlink all captured photos, together with these obscured by clouds, Φsat-2 processes these photos straight in orbit, making certain that solely clear, usable photos are despatched again to Earth. Developed by KP Labs, this utility may also classify clouds and supply insights into cloud distribution. This offers customers extra flexibility when it’s time to resolve whether or not a picture is usable or not.
• Road map technology.The Sat2Map utility, developed by CGI, converts satellite imagery into road maps. This functionality is especially useful for emergency response groups, enabling them to establish accessible roads throughout disasters comparable to floods or earthquakes. When the satellite orbits over the affected space and acquires photos, the photographs are handed to the onboard processer that can establish streets and generate a corresponding map. Initially, this utility will likely be demonstrated over Southeast Asia, showcasing its potential to assist in disaster administration.
• Maritime vessel detection.The maritime vessel detection utility, developed by CEiiA, makes use of machine studying strategies to mechanically detect and classify vessels in specified areas, facilitating the monitoring of actions like unlawful fishing. This utility underscores the satellite’s position in supporting maritime safety and environmental conservation efforts.
• On-board picture compression and reconstruction. Developed by GEO-Ok, this utility is liable for compressing photos on board. By considerably lowering file sizes, this utility will increase the amount and velocity of information downloads. After being downlinked to the bottom, the photographs are reconstructed utilizing a devoted decoder. The primary demonstrations of this know-how will happen over Europe, specializing in the detection of buildings.