PHOBOS

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.

Using Genetics algorithm with the orbital parameters as the equivalent of chromosomes, the complete set of which compose an individual: the orbit. For each individual, we can compute a function of performance which will be used to compare it to others.

Using the orbit inversion code named Genoid (GENetic Orbit IDentification), relies on a metaheuristic method and a dynamical model of the solar system. Using two dynamical models: a simple Keplerian model and a full N-body problem which includes the gravitational field of the primary asteroid up to 4th order. To minimize the search-time for an orbital solution, we first used the Keplerian model to explore a wide space of solutions, even based on a limited number of astrometric positions. We then ran the full N-body model on a set of parameters around the Keplerian solution to search for the most accurate solution when taking into account the full physical behavior of dynamical systems.

The implementation will run in python or java program that will develop the model, to chaise Hazardous Asteroid (PHA), Near Earth Asteroid (NEA), or Known Astroid (KA) . using genetic algorithms with our own secreat sauce as metaheuristic.

https://spaceapps.hackpad.com/FIEC-MACHINE-LEARGNI...

Given the genetic algorithm basis, it will proceed to modify it to siut our problema, in wich ourinitial populationwill be theminorplanetcenterasteroids.

With this data we willfocus ongetting the 7 parameters we set out to determine the asteroid, wich wasstored in a Json ormatrix.

Then withthe fitness(providedabove) willproceed to look for thosecandides whowill be theparents and are selected (followingthe logic of the geneticalgorithm).

With theseparents wegenerate thechildren and procedes with themutation, thecondidtion isreviewed ifthe children are select or removed (algorithm logic). This cyclewill remainuntil youfind theoptimal, as long as they do note xceed thethirtieth interaction, because if exceded, it isdeleted and start again because there is nothing.

This seeks to detect those orbits of asteroids that were not detected by satellites to determine which can be dangerous for the planet earth. The results are displayed through charts, which indicate those orbits that were detected by the generic algorithm.

https://spaceapps.hackpad.com/FIEC-MACHINE-LEARGNI...

methahuristic genetics algorithms,, numpy, scypy, DEAP Python, Genoid Algorithm, mino planet center data