Year: 2020
Type: article
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.
Authors: B. Henghes, O. Lahav, D. W. Gerdes, H. W. Lin, R. Morgan, T. M. C. Abbott, M. Aguena, S. Allam, J. Annis, S. Avila, E. Bertin, D. Brooks, D. L. Burke, A. Carnero Rosell, M. Carrasco Kind, J. Carretero, C. Conselice, M. Costanzi, L. N. da Costa, J. De Vicente, S. Desai, H. T. Diehl, P. Doel, S. Everett, I. Ferrero, J. Frieman, J. García-Bellido, E. Gaztanaga, D. Gruen, R. A. Gruendl, J. Gschwend, G. Gutierrez, W. G. Hartley, S. R. Hinton, K. Honscheid, B. Hoyle, D. J. James, K. Kuehn, N. Kuropatkin, J. L. Marshall, P. Melchior, F. Menanteau, R. Miquel, R. L. C. Ogando, A. Palmese, F. Paz-Chinchón, A. A. Plazas, A. K. Romer, C. Sánchez, E. Sanchez, V. Scarpine, M. Schubnell, S. Serrano, M. Smith, M. Soares-Santos, E. Suchyta, G. Tarle, C. To, R. D. Wilkinson
Institutions: University College London, University of Michigan, University of Wisconsin–Madison, Cerro Tololo Inter-American Observatory, Universidade de São Paulo, Laboratório Interinstitucional de e-Astronomia, Fermi National Accelerator Laboratory, Instituto de Física Teórica, Universidad Autónoma de Madrid, Centre National de la Recherche Scientifique, Institut d'Astrophysique de Paris, Université Pierre-et-Marie-Curie, SLAC National Accelerator Laboratory, Kavli Institute for Particle Astrophysics and Cosmology, Stanford University, Universidad de La Laguna, Instituto de Astrofísica de Canarias, University of Illinois Urbana-Champaign, National Center for Supercomputing Applications, Institute for High Energy Physics, Barcelona Institute of Science and Technology, University of Nottingham, University of Manchester, Trieste Astronomical Observatory, Institute for Fundamental Physics of the Universe, National Observatory, Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas, Indian Institute of Technology Hyderabad, University of California, Santa Cruz, University of Oslo, University of Chicago, Institute of Space Sciences, Institut d'Estudis Espacials de Catalunya, University of Geneva, ETH Zurich, The University of Queensland, The Ohio State University, Max Planck Institute for Extraterrestrial Physics, Ludwig-Maximilians-Universität München, Center for Astrophysics Harvard & Smithsonian, Lowell Observatory, Australian Astronomical Optics, Texas A&M University, Princeton University, Institució Catalana de Recerca i Estudis Avançats, University of Cambridge, University of Sussex, University of Pennsylvania, University of Southampton, Oak Ridge National Laboratory
Language: English
Topic: Astro and Planetary Science
Subfield: Space and Planetary Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: bronze
Funders: National Science Foundation, U.S. Department of Energy, University of Pennsylvania, Ohio State University, University of Chicago, University of Portsmouth, Centres de Recerca de Catalunya, University College London, European Commission, University of Sussex, Deutsche Forschungsgemeinschaft, Generalitat de Catalunya, Ministério da Ciência, Tecnologia e Inovação, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro, Financiadora de Estudos e Projetos, Ministerio de Ciencia e Innovación, Institut de Física d'Altes Energies, University of Illinois at Urbana-Champaign, Office of Science, Science and Technology Facilities Council, European Regional Development Fund, Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas, High Energy Physics, Integrated Electronics Engineering Center, Binghamton University, Argonne National Laboratory, Fermilab, Lawrence Berkeley National Laboratory, FP7 Ideas: European Research Council, SLAC National Accelerator Laboratory
Awards: University of Sussex Astronomy Consolidated Grant 2020-2023, G1265542407, Capitalizing on Gravitational Shear, G1328166135, G154696372, UCL Astrophysics Consolidated Grant 2018-2021, Testing the Dark Energy Paradigm and Measuring Neutrino Mass with the Dark Energy Survey, G1682672702, PROPOSAL TO EXPLORE THE FUNDAMENTAL CONSTITUENTS OF THE UNIVERSE FUNDING YEARS FY 2018-2020, UCL Centre for Doctoral Training in Data Intensive Science and Technologies, G1993551506, G2074038056, CASU Equipment 2016/17, G2401681081, Novel applications of machine learning in cosmology and beyond, G265847165, Additional AGP funding - supplementary to Sussex Consolidated Grant ST/L000652/1, G3154116105, G3207356259, G3715052068, The Dark Energy Survey Data Management Operations, University of Sussex Astronomy Consolidated Grant 2017-2020, Astrophysics and Cosmology Research at the JBCA 2020-2023, G3906089732, G393177772, G3968781304, G419118642, G4404904460, G454676879, Understanding the Origin of Cosmic Structure, G496129201, G5702163051, Cosmology from Surveys, G585908603, G6480793128, G6619390584, G6676276723, G716412294, G7290792616, G7711421660, G7788408655, G7835623888, UCL Astrophysics Consolidated Grant 2015-2018, Collaborative Research: The Dark Energy Survey Data Management Operations, Astrophysics and Cosmology - Sussex Consolidated Grant, G86560745
OpenAlex ID: W3088486556
