Using AI to scan the Earth

2025-12-03 · Source: artificial intelligence Archives - SpaceNews · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Intermediate, quick

Summary

NASA's Jet Propulsion Laboratory (JPL), in collaboration with U.K. startup Open Cosmos and Irish startup Ubotica Technologies, demonstrated a Dynamic Targeting solution that uses AI to enable Earth observation satellites to autonomously capture cloud-free imagery. This system allows a satellite to analyze its orbital path, identify clouds, and adjust its sensors to gather clear images within 50 to 90 seconds while traveling at 7.5 kilometers per second at an altitude of 500 kilometers. The demonstration, conducted in July, utilized a hyperspectral sensor on Open Cosmos' CogniSat-6, with Ubotica's payload running JPL's algorithm. This technology, recognized with a Space AI Breakthrough award, represents a significant advancement in satellite autonomy, moving beyond indiscriminate image collection to targeted data acquisition.

Key takeaway

For AI Scientists developing space-based applications, this Dynamic Targeting demonstration highlights the critical role of on-board AI and edge processing for real-time autonomous operations. You should focus on optimizing algorithms for rapid inference and sensor control, enabling satellites to make immediate, data-driven decisions without human intervention. This approach is essential for enhancing efficiency and data quality in dynamic space environments.

Key insights

AI-powered dynamic targeting enables satellites to autonomously capture cloud-free Earth observation imagery.

Principles

• Prioritize targeted data acquisition over indiscriminate imaging.
• Integrate AI and edge processing for real-time decision-making.

Method

A satellite scans its orbital path, an AI algorithm identifies clouds, and the system autonomously adjusts sensor pointing to collect cloud-free images, accounting for Earth's rotation and curvature.

In practice

• Deploy AI for real-time cloud detection in satellite imaging.
• Utilize edge processing for rapid in-orbit decision-making.
• Integrate look-ahead sensors for proactive targeting.

Topics

• Dynamic Targeting
• Satellite Autonomy
• Earth Observation
• Space-based Edge AI
• Cloud Avoidance

Best for: Computer Vision Engineer, AI Scientist, AI Engineer, AI Researcher, Research Scientist

Related on AIssential

• Optimizing Earth Observation Satellite Schedules under Unknown Operational Constraints: An Active Constraint Acquisition Approach — Interleaving constraint acquisition with optimization efficiently solves EO satellite scheduling under unknown operational constraints.
• AI Processing of Earth Images Can Now Run in Space — Onboard AI processing on satellites significantly reduces data latency for Earth observation, enabling real-time insights.
• A satellite just learned to find things on its own — here’s what that means — An Earth observation satellite autonomously processed sensor data using an on-orbit vision-language model, marking a significant edge AI milestone.
• Managing traffic in space — Astrodynamics and AI are crucial for managing escalating space traffic and ensuring orbital sustainability.
• Loft Orbital to test AI models on spacecraft for Earth observation — Onboard AI processing on satellites enables real-time Earth observation and rapid response without extensive data downlink.
• Reinforcement Learning-Based Dynamic Management of Structured Parallel Farm Skeletons on Serverless Platforms — AI-driven dynamic scaling improves QoS and resource efficiency for parallel processing on serverless platforms.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by artificial intelligence Archives - SpaceNews.