Machine Automated Resolution of Keplerian Elements

For this challenge, we invite you to become "virtual contributors" to the Asteroid Grand Challenge and develop a hypothetical method, concept note or simple prototype that demonstrates how Machine Learning could be used to help us avoid the same fate as the dinosaurs.

When an observer on the Earth captures some cartesian orbital elements there is a need to easily convert those elements in to keplerian elements. There is also a need to find out if the tracked object in question is already cataloged. The system I built uses machine learning to derive keplerian elements and gives a probability of a matched ellipse and the probability that the solved for ellipse matches a cataloged orbit.

There is a web based front end for ease of use and sweet data graphics.

For this project I used Pluto as a control. I took a span of ephemeris data and solved it's orbital ellipse.This process should extend to minor bodies and near earth asteroids.

WebGL, Javascript, Python, Tensorflow (Google), Apache, Redis