Exploring Survey Operations and Machine Learning for the Dark Energy Spectroscopic Instrument
Martin White, Professor
Physics
Applications for Fall 2026 are closed for this project.
The Dark Energy Spectroscopic Instrument (DESI) survey is currently mapping the positions of millions of galaxies, stars, and quasars across the night sky from the Mayall Telescope at Kitt Peak National Observatory. DESI aims to make the world’s largest 3D map of the universe to understand the effects of dark energy throughout the universe. Each night, DESI observes anywhere between one to a few dozen exposures, where each exposure is associated with a unique pointing of the telescope. This project aims to use advanced machine learning and AI to improve the efficiency of these observations.
Role: The student will learn how the day to day survey operation of the DESI survey is run as well how astronomical data is processed. They will also learn how AI/ML is changing this workflow and have the opportunity to contribute to these efforts.
Qualifications: - Interest in astronomy/cosmology and the application of ML/AI to this regime.
- Basic python experience required.
- Prior AI or ML experience useful, but not required.
Day-to-day supervisor for this project: Dylan Green, Post-Doc
Hours: to be negotiated
Off-Campus Research Site: Lawrence Berkeley National Lab Building 50 and remote work
Related website: https://desi.lbl.gov
Related website: https://data.desi.lbl.gov