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

Tags

Readers

  • Geotechnical Engineering.
  • Image Processing and Computer Vision.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Space
  • Space - Space Objects