Abstract
The purpose of this study is to make a prediction of combinations of orbital parameters for yet undiscovered potentially hazardous asteroids (PHAs) with the use of machine learning algorithms. The proposed approach aims at outlining subgroups of all major groups of near-Earth asteroids (NEAs) with high concentration of PHAs in them. The approach is designed to obtain meaningful results and easy-understandable boundaries of the PHA subgroups in 2- and 3-dimensional subspaces of orbital parameters. Boundaries of these PHA subgroups were found mainly by the use of Support Vector Machines algorithm with RBF kernel. Additional datasets of virtual asteroids were generated to handle sufficient amount of training and test data, as well as to emulate undiscovered asteroids. This synthetic data helped in revealing ‘XX’-shaped region with high concentration of PHAs in the (ω, q) plane. Boundaries of this region were used to split all NEAs into several domains. For each domain the subgroups of PHAs were outlined in different subspaces of orbital parameters. Extracted subgroups have high PHA purity (∼90%) and contain ∼90% of all real and virtual PHAs. Obtained results can be useful for planning future PHA discovery surveys or asteroid-hunting space missions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Beeson, C.L., Elvis, M., Galache, J.L.: Scaling near Earth asteroid (NEA) characterization rates. Harv. Undergrad. Res. J. Astrophys. 6(1), (2013). http://thurj.org/research/2013/05/4458/
Galache, J.L., Beeson, C.L., McLeod, K.K., Elvis, M.: The need for speed in near-Earth asteroid characterization. Planet. Space Sci. 111, 155–166 (2015.) https://arxiv.org/pdf/1504.00712.pdf
Mainzer, A., Grav, T., Bauer, J., Conrow, T., Cutri, R.M., Dailey, J., Fowler, J., Giorgini, J., Jarrett, T., Masiero, J., Spahr, T., Statler, T., Wright, E.L.: Survey simulations of a new near-Earth asteroid detection system. Astron. J. 149(5), 172 (2015.) 17pp
Myhrvold, N.: Comparing NEO search telescopes. Publ. Astron. Soc. Pac. 128(962), 045004 (2016.) http://iopscience.iop.org/article/10.1088/1538-3873/128/962/045004/pdf
Shao, M., Turyshev, S.G., Spangelo, S., Werne, T., Zhai, C.: A constellation of SmallSats with synthetic tracking cameras to search for 90% of potentially hazardous near-Earth objects. Astron. Astrophys. 603, A126 (2017)
Bottke, W.F., Morbidelli, A., Jedicke, R., Petit, J.M., Levison, H.F., Michel, P., Metcalfe, T.S.: Debiased orbital and absolute magnitude distribution of the near-Earth objects. Icarus. 156(2), 399–433 (2002)
Granvik, M., Morbidelli, A., Jedicke, R., Bolin, B., Bottke, W.F., Beshore, E., Vokrouhlický, D., Delbò, M., Michel, P.: Super-catastrophic disruption of asteroids at small perihelion distances. Nature. 530, 303–306 (2016)
Jedicke, R., Bolin, B., Granvik, M., Beshore, E.: A fast method for quantifying observational selection effects in asteroid surveys. Icarus. 266, 173–188 (2016)
Mainzer, A., Grav, T., Masiero, J., Bauer, J., McMillan, R.S., Giorgini, J., Spahr, T., Cutri, R.M., Tholen, D.J., Jedicke, R., Walker, R., Wright, E., Nugent, C.R.: Characterizing subpopulations within the near-Earth objects with NEOWISE: preliminary results. Astrophys. J. 752(2), 110 (2012.), 16pp
Tricarico, P.: The near-Earth asteroid population from two decades of observations. Icarus. 284, 416–423 (2017)
Granvik, M., Vaubaillon, J., Jedicke, R.: The population of natural Earth satellites. Icarus. 218, 262–277 (2012)
Fedorets, G., Granvik, M., Jedicke, R.: Orbit and size distributions for asteroids temporarily captured by the Earth-Moon system. Icarus. 285, 83–94 (2017)
Feigelson, E.D., Babu, G.J.: Modern Statistical Methods for Astronomy: With R Applications. Cambridge University Press, New York (2012)
Scikit-learn official website. http://scikit-learn.org/stable/
Harrington, P.: Machine Learning in Action. Manning, Greenwich (2012)
Marsland, S.: Machine learning: an algorithmic perspective Machine Learning & Pattern Recognition, 2nd edn. Chapman & Hall/CRC, Boca Raton (2014)
Madhulatha, T.S.: An overview on clustering methods. IOSR J Eng. 2(4), 719–725 (2012.) https://arxiv.org/ftp/arxiv/papers/1205/1205.1117.pdf
Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the 2nd ACM International Conference on Knowledge Discovery and Data Mining (KDD), Portland, OR, pp. 226–231. (1996). http://www.dbs.ifi.lmu.de/Publikationen/Papers/KDD-96.final.frame.pdf
Gronchi, G.F., Valsecchi, G.B.: On the possible values of the orbit distance between a near-Earth asteroid and the Earth. Mon. Not. R. Astron. Soc. 429, 2687–2699 (2013)
Blanco-Silva, F.J.: Learning SciPy for Numerical and Scientific Computing. Packt Publishing. www.packtpub.com (2013)
Schunová-Lilly, E., Jedicke, R., Vereš, P., Denneau, L., Wainscoat, R.J.: The size-frequency distribution of H > 13 NEOs and ARM target candidates detected by Pan-STARRS1. Icarus. 284, 114–125 (2017)
Acknowledgments
The author is grateful to: the organizers of the global hackathon NASA Space Apps Challenge 2016 for offering awesome challenges, one of which inspired him for the current research; the officials of Kirovograd Flight Academy of the National Aviation University, who organized and hosted first-ever Space Apps Challenge in Ukraine, particularly—Alexey Izvalov and Sergey Nedelko; the members of the team Asterion—CYA, particularly—Eugene Scherbina and Andrij Blakitnij, who’s hard labor and enthusiasm pushed the boundaries of impossible; Ian Webster—developer of Asterank for collecting and sharing the asteroid database and for collaborating with the author on including PHA ranking features to the service, Giovanni F. Gronchi from the University of Pisa for sharing his paper, Carrie R. Nugent from IPAC/Caltech for referring to important papers and pointing the need of testing obtained results on the debiased data, which will be the subject of the future work. The author would also like to show his gratitude to all contributors to the Scikit-learn project—open-source software for machine learning that provides easy access to sophisticated math and encourages experimenting with different algorithms.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Pasko, V. (2018). Prediction of Orbital Parameters for Undiscovered Potentially Hazardous Asteroids Using Machine Learning. In: Vasile, M., Minisci, E., Summerer, L., McGinty, P. (eds) Stardust Final Conference. Astrophysics and Space Science Proceedings, vol 52. Springer, Cham. https://doi.org/10.1007/978-3-319-69956-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-69956-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69955-4
Online ISBN: 978-3-319-69956-1
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)