Identification of asteroids trapped inside three-body mean motion resonances: A machine-learning approach
abstract
In this paper, we apply the following machine-learning methods that do not require numerical integration — namely, k-Nearest Neighbours, Decision tree, Gradient boosting and Logistic regression — to the identification of three-body resonant asteroids in the main belt. It is shown that the results of the identification by machine-learning methods are accurate and take significantly less time than numerical integration (seconds versus days). We have identified 404 new asteroids subjected to the three-body resonance 4J-2S-1 using a machine-learning methodology.