Improving orbit prediction accuracy through supervised machine learning

Hao Peng, Xiaoli Bai

Research output: Contribution to journalArticlepeer-review

51 Scopus citations


Due to the lack of information such as the space environment condition and resident space objects’ (RSOs’) body characteristics, current orbit predictions that are solely grounded on physics-based models may fail to achieve required accuracy for collision avoidance and have led to satellite collisions already. This paper presents a methodology to predict RSOs’ trajectories with higher accuracy than that of the current methods. Inspired by the machine learning (ML) theory through which the models are learned based on large amounts of observed data and the prediction is conducted without explicitly modeling space objects and space environment, the proposed ML approach integrates physics-based orbit prediction algorithms with a learning-based process that focuses on reducing the prediction errors. Using a simulation-based space catalog environment as the test bed, the paper demonstrates three types of generalization capability for the proposed ML approach: (1) the ML model can be used to improve the same RSO's orbit information that is not available during the learning process but shares the same time interval as the training data; (2) the ML model can be used to improve predictions of the same RSO at future epochs; and (3) the ML model based on a RSO can be applied to other RSOs that share some common features.

Original languageEnglish (US)
Pages (from-to)2628-2646
Number of pages19
JournalAdvances in Space Research
Issue number10
StatePublished - May 15 2018

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Astronomy and Astrophysics
  • Geophysics
  • Atmospheric Science
  • Space and Planetary Science
  • Earth and Planetary Sciences(all)


  • Orbit prediction
  • Resident space object
  • Supervised machine learning
  • Support vector machine


Dive into the research topics of 'Improving orbit prediction accuracy through supervised machine learning'. Together they form a unique fingerprint.

Cite this