Machine learning-based solution of Kepler's equation

Maozhang Zheng, Jianjun Luo, Zhaohui Dang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this study, an analytical solution of elliptical Kepler's equation, which gives the position of a celestial body moving in orbit as a function of time, is designed by using artificial intelligence techniques. For the eccentric anomaly, Kepler's equation is a transcendental equation with no precise analytical solution. In this paper, a high precision approximate analytical solution is presented to determine eccentric anomaly. The proposed method is based on machine learning where a non-iterative accurate solution is learned from training data. The solution to Kepler's solution is created using an artificial neural network based on the universal approximation theorem. Simulation results show that this solution is computationally efficient and has a constant complexity.

Original languageEnglish
Title of host publicationThird International Conference on Computer Science and Communication Technology, ICCSCT 2022
EditorsYingfa Lu, Changbo Cheng
PublisherSPIE
ISBN (Electronic)9781510661240
DOIs
StatePublished - 2022
Event3rd International Conference on Computer Science and Communication Technology, ICCSCT 2022 - Beijing, China
Duration: 30 Jul 202231 Jul 2022

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12506
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference3rd International Conference on Computer Science and Communication Technology, ICCSCT 2022
Country/TerritoryChina
CityBeijing
Period30/07/2231/07/22

Keywords

  • Kepler's equation
  • machine learning
  • neural network

Fingerprint

Dive into the research topics of 'Machine learning-based solution of Kepler's equation'. Together they form a unique fingerprint.

Cite this