AI Copilot Boosts Telescope Observations at Chile’s Cerro Tololo Observatory

A new artificial‑intelligence system developed by researchers at Northwestern University, the University of Chicago and Fermilab is being used as an automated “copilot” for planning observations with large telescopes. Integrated into the SkAI (AI Institute for the Sky) platform, the deep‑learning model was trained on years of data from the Dark Energy Survey and can generate and adjust observation schedules in real time, accounting for clouds, humidity, turbulence and moonlight.

The technology was field‑tested at the Cerro Tololo Inter‑American Observatory in Chile, where it programmed the 4‑metre telescope’s Dark Energy Camera – a 570‑megapixel instrument used to study distant galaxies, supernovae and dark energy. By dynamically adapting to changing atmospheric conditions, the AI copilot improves data quality and reduces the risk of wasted telescope time caused by poor planning.