Φsat-2 "GO" For Launch For Pioneering AI Earth Observation Mission

In an ambitious leap for satellite technology and Earth observation, the European Space Agency (ESA) is set to launch Φsat-2 (pronounced phisat-2), a 6U cubesat that exemplifies the integration of Artificial Intelligence (AI) into space missions.

Measuring a compact 22 x 10 x 33 cm, this miniature satellite is equipped with a sophisticated multispectral instrument capable of capturing images in seven different bands, alongside a panchromatic band, covering the visible to near-infrared spectrum.

The primary objective of Φsat-2 is to harness AI for smarter, more efficient Earth observation. The satellite's on-board AI applications enhance its capability to analyze and process data autonomously, a significant advancement in satellite technology.

One standout AI application on Φsat-2 is its ability to automatically detect and discard cloudy images. Traditional satellites downlink all captured images, including those obscured by clouds, which are of limited use for most Earth observation purposes. However, Φsat-2's AI processes these images in situ, ensuring only clear, usable images are sent back to Earth. This innovation not only conserves bandwidth but also speeds up data transmission, making the satellite's operations more efficient.

Another notable application converts satellite imagery into street maps. This capability is particularly beneficial for emergency response teams, enabling them to identify accessible roads during disasters such as floods or earthquakes. Initially, this application will be demonstrated over Southeast Asia, showcasing its potential to aid in crisis management.

Additionally, Φsat-2’s AI can detect marine vessels in specified regions, facilitating the monitoring of activities like illegal fishing. This application underscores the satellite’s role in supporting maritime security and environmental conservation efforts.

The satellite also features advanced AI for deep image compression. By significantly reducing file sizes, this application increases the volume and speed of data downloads. The first demonstrations of this technology will occur over Europe, focusing on the detection of buildings.

In a bid to further expand the satellite’s capabilities, the OrbitalAI Φsat-2 challenge, organized by ESA’s Φ-lab, aims to incorporate two additional AI applications. This initiative invites innovators to contribute to the satellite’s suite of AI tools, fostering collaboration and technological advancement.

Scheduled for liftoff in 2024, Φsat-2 will share its journey into orbit with other satellites aboard a SpaceX Falcon 9 rocket, launching from Vandenberg Air Force Base in California, USA. The mission is a collaborative effort, with Open Cosmos as the prime contractor, supported by an industrial consortium including Ubotica, GGI, CEiiA, GEO-K, KP-Labs, and SIMERA.

Through Φsat-2, ESA continues to push the boundaries of Earth observation, demonstrating the transformative potential of AI in space technology. As this innovative satellite prepares for its mission, it promises to deliver smarter, more efficient ways of monitoring our planet, paving the way for future advancements in satellite-based Earth observation.