Machine Learning for Searching the Dark Energy Survey for Trans-Neptunian Objects

Henghes, B.; Lahav, O.; Gerdes, D. W.; Lin, H. W.; Morgan, R.; Abbott, T. M. C.; Aguena, M.; Allam, S.; Annis, J.; Avila, S.; Bertin, E.; Brooks, D.; Burke, D. L.; Rosell, A. Carnero; Kind, M. Carrasco; Carretero, J.; Conselice, C.; Costanzi, M.; da Costa, L. N.; De Vicente, J.; Desai, S.; Diehl, H. T.; Doel, P.; Everett, S.; Ferrero, I.; Frieman, J.; Garcia-Bellido, J.; Gaztanaga, E.; Gruen, D.; Gruendl, R. A.; Gschwend, J.; Gutierrez, G.; Hartley, W. G.; Hinton, S. R.; Honscheid, K.; Hoyle, B.; James, D. J.; Kuehn, K.; Kuropatkin, N.; Marshall, J. L.; Melchior, P.; Menanteau, F.; Miquel, R.; Ogando, R. L. C.; Palmese, A.; Paz-Chinchon, F.; Plazas, A. A.; Romer, A. K.; Sanchez, C.; Sanchez, E.; Scarpine, V.; Schubnell, M.; Serrano, S.; Smith, M.; Soares-Santos, M.; Suchyta, E.; Tarle, G.; To, C. und Wilkinson, R. D. (2021): Machine Learning for Searching the Dark Energy Survey for Trans-Neptunian Objects. In: Publications of the Astronomical Society of the Pacific, Bd. 133, Nr. 1019, 14501

Abstract

In this paper we investigate how implementing machine learning could improve the efficiency of the search for Trans-Neptunian Objects (TNOs) within Dark Energy Survey (DES) data when used alongside orbit fitting. The discovery of multiple TNOs that appear to show a similarity in their orbital parameters has led to the suggestion that one or more undetected planets, an as yet undiscovered Planet 9, may be present in the outer solar system. DES is well placed to detect such a planet and has already been used to discover many other TNOs. Here, we perform tests on eight different supervised machine learning algorithms, using a data set consisting of simulated TNOs buried within real DES noise data. We found that the best performing classifier was the Random Forest which, when optimized, performed well at detecting the rare objects. We achieve an area under the receiver operating characteristic (ROC) curve, (AUC) = 0.996 0.001. After optimizing the decision threshold of the Random Forest, we achieve a recall of 0.96 while maintaining a precision of 0.80. Finally, by using the optimized classifier to pre-select objects, we are able to run the orbit-fitting stage of our detection pipeline five times faster.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Physik
• Themengebiete: 500 Naturwissenschaften und Mathematik > 530 Physik
• ISSN: 0004-6280
• Sprache: Englisch