CGI's Insula Platform Powers AI Earth Observation for ESA's Φsat-2 Mission

Jun 24, 2026
CGI is supporting the European Space Agency's Φsat-2 mission with its Insula platform, which processes and harmonizes satellite data for AI-driven Earth observation and analytics.

CGI is supporting the European Space Agency (ESA)'s Φsat-2 mission with its Insula platform, announced in a press release. The platform enables artificial intelligence applications for Earth observation by processing and harmonizing large volumes of satellite data.

Developed by CGI's team in Italy, Insula provides calibrated and geolocated datasets to scientific communities and AI application providers. It supports functions such as trend detection, anomaly monitoring, and predictive modeling. Since becoming publicly available in June 2025, Insula has served more than 3,000 users and delivered over 10,000 multispectral images.

The Φsat-2 satellite, one of ESA's most advanced small satellites, runs AI directly onboard to enhance observation capabilities. It performs independent tasks such as cloud detection, maritime vessel classification, street map generation, environmental monitoring, and fire detection. The mission demonstrates how onboard processing can deliver timely, high-quality information to Earth observation stakeholders.

CGI’s collaboration with ESA builds on over a decade of work in Earth observation, mission operations, and planetary monitoring, supporting the delivery of advanced technologies to the scientific community.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Industrial AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Industrial AI Weekly

The latest advancements in smart manufacturing, predictive maintenance, AI-driven quality control, supply chain & more.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.