Machine Learning for Searching the Dark Energy Survey for Trans-Neptunian Objects
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.
- Research Organization:
- SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States); Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Univ. of Michigan, Ann Arbor, MI (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Science (SC), High Energy Physics (HEP); National Science Foundation (NSF); Science and Technology Facilities Council (STFC) (United Kingdom); European Research Council (ERC); Spain Ministry of Science, Innovation and Universities (MICINN); Brazilian Instituto Nacional de Ciencia e Tecnologia (INCT); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
- Contributing Organization:
- DES Collaboration
- Grant/Contract Number:
- AC02-76SF00515; SC0019193; ST/P006736/1; ST/R000476/1; ST/M001334/1; 291329; 240672; 306478; FP7/2007-2013; TESTDE FP7/291329; AC02- 876 07CH11359; SEV-2016-0588; SEV-2016-0597; MDM-2015-0509; PGC2018-094773; PGC2018-102021; ESP2017-89838; AST-1536171; AST-1138766; 465376/2014-2; ID 2012B-0001; AC02-07CH11359; AC05-00OR22725
- OSTI ID:
- 1767943
- Alternate ID(s):
- OSTI ID: 1706151; OSTI ID: 1782119; OSTI ID: 1807211
- Report Number(s):
- FERMILAB-PUB-20-452-AE; DES-2020-0553; arXiv:2009.12856; TRN: US2206422
- Journal Information:
- Publications of the Astronomical Society of the Pacific (Online), Vol. 133, Issue 1019; ISSN 1538-3873
- Publisher:
- Astronomical Society of the Pacific (ASP)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Cosmological constraints from DES Y1 cluster abundances and SPT multiwavelength data
DES Y1 results: Splitting growth and geometry to test Λ CDM