Finding Space Junk with the World’s Biggest Telescopes

Finding Space Junk with the World’s Biggest Telescopes

2020

Astronomers from the Dark Energy Survey rely on images of deep space to understand the nature of the universe, but these images are often polluted with “space junk”: asteroids, comets, satellites, or other objects from our own solar system obstructing the telescope’s view. In order to perform their analysis, scientists must first manually identify and mask out such objects from images, a time-consuming process. With leads Michael Troxel, Dan Scolnic, and Chris Walter, we’ve leveraged deep learning-based computer vision techniques to build models to automatically identify and localize space junk in deep space imagery.

Project Lead: Dan ScolnicMichael TroxelChris Walter

Click here to view the team’s final project

Contact

Mathematics

Related People

Physics

Math

Data Science