Dynos

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.

We have worked on an MVP of a system that would identify NEOs on a series of images, and using orbit information be able to tag them on images (from archives or new streams).

We have thought of a way to detect changes in a sequence of two images, generate features that would feed a machine learning pipeline. We also made data accessible to machines by providing a REST API to some features from HORIZONS System and html tables spread through sites.

http://www.minorplanetcenter.net/

http://www.zooniverse.org

http://ssd.jpl.nasa.gov/redirect/horizons.html

Java, Python