Learning Capabilities of Neural Networks and Keplerian Dynamics

Damien Guého


Machine learning (ML) tools, especially deep neural networks (DNNs) have garnered significant attention in the last decade; however, it is not clear whether ML tools can learn the inherent characteristics of dynamical model (such as conservation laws) from the training data set. This paper considers the effectiveness of DNNs in learning dynamical system models by considering the Keplerian two-body problem. Training a DNN with data from a single revolution produces poor performance when predicting motion on subsequent revolutions. By incorporating deviations from constancy of angular momentum and total energy into the loss function for the DNN, predictive performance improves significantly. Further improvements appear when a richer training data set (generated from a number of orbits with different in orbital element values) is employed.

2018 AIAA/AAS Astrodynamics Specialist Conference, Snowbird, UT
Click the Cite button above to import publication metadata into your reference management software.
Damien Guého
Damien Guého
Aerospace Engineer

My research interests include data-driven modeling and system identification, analysis of complex dynamical systems, stochastic analysis and uncertainty quantification.