%0 Journal Article
%4 sid.inpe.br/mtc-m21c/2020/08.04.12.29
%2 sid.inpe.br/mtc-m21c/2020/08.04.12.29.06
%@doi 10.1093/mnras/staa1463
%@issn 0035-8711
%@issn 1365-2966
%T Machine learning classification of new asteroid families members
%D 2020
%8 Jun
%9 journal article
%A Carruba, Valerio,
%A Aljbaae, Safwan,
%A Domingos, R. C.,
%A Lucchini, A.,
%A Furlaneto, P.,
%@affiliation Universidade Estadual Paulista (UNESP)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Universidade Estadual Paulista (UNESP)
%@affiliation Universidade Estadual Paulista (UNESP)
%@affiliation Universidade Estadual Paulista (UNESP)
%@electronicmailaddress valerio.carruba@unesp.br
%@electronicmailaddress safwan.aljbaae@inpe.br
%B Monthly Notices of the Royal Astronomical Society
%V 496
%N 1
%P 540-549
%K software: data analysis – celestial mechanics – minor planets, asteroids: general.
%X Asteroid families are groups of asteroids that are the product of collisions or of the rotational fission of a parent object. These groups are mainly identified in proper elements or frequencies domains. Because of robotic telescope surveys, the number of known asteroids has increased from 10 000 in the early 1990s to more than 750 000 nowadays. Traditional approaches for identifying new members of asteroid families, like the hierarchical clustering method (HCM), may struggle to keep up with the growing rate of new discoveries. Here we used machine learning classification algorithms to identify new family members based on the orbital distribution in proper (a, e, sin (i)) of previously known family constituents. We compared the outcome of nine classification algorithms from stand-alone and ensemble approaches. The extremely randomized trees (ExtraTree) method had the highest precision, enabling to retrieve up to 97 per cent of family members identified with standard HCM.
%@language en
%3 carruba_mahine.pdf