Understanding the optical lightcurves of LEO spacecraft: the application of machine learning techniques
Abstract
We have been applying sophisticated machine learning techniques to studies of lightcurves in order to classify stellar variability. These methods worked well, except for the lowest signal to noise data where there is little signal de?ning the detailed shape. The same techniques can be applied to an in-depth study of lightcurves from low Earth orbiting satellites. Here we expect rotation (both controlled and tumbling) and phase effects to be important, but the detailed shapes could also depend on surface composition. In future, these techniques could also be applied to hyperspectral data which may betray signals from partially hibernating instruments.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jul 24, 2019
- Source ID
- FA95501817017
Entities
People
- Don Pollacco
Organizations
- Air Force Office of Scientific Research
- United States Air Force
- University of Warwick