Machine learning techniques meet binaries
(2019) EWASS 2019: Special Session 22 Stellar Multiplicity in the Gaia Era: Where do we Stand? In Memorie della Societa Astronomica Italiana - Journal of the Italian Astronomical Society 90(3). p.327-339- Abstract
We briefly review the various machine learning methods and discuss how they can be used in efficient identification and analysis of spectroscopic binary stars. They can be treated as complementary to conventional methods, and we argue that some amount of human oversight is always needed and in fact highly beneficial when employing machine learning. We propose that a general dimensionality reduction technique can serve to diagnose and classify a given data set, and in case of GALAH spectra, our method quite effectively reveals a population of SB2 and SB3 systems. Once identified, the binary spectra can be analysed with the help of generative models, which can be constructed using machine learning techniques such as The Cannon and The... (More)
We briefly review the various machine learning methods and discuss how they can be used in efficient identification and analysis of spectroscopic binary stars. They can be treated as complementary to conventional methods, and we argue that some amount of human oversight is always needed and in fact highly beneficial when employing machine learning. We propose that a general dimensionality reduction technique can serve to diagnose and classify a given data set, and in case of GALAH spectra, our method quite effectively reveals a population of SB2 and SB3 systems. Once identified, the binary spectra can be analysed with the help of generative models, which can be constructed using machine learning techniques such as The Cannon and The Payne. Furthermore, in the case of spectroscopically unresolved multiple stars, we can recover the multiple contributions to an observed spectrum by reversing the process and proceeding from analysis to identification.
(Less)
- author
- Traven, G. LU ; Čotar, K. ; Merle, T. ; van der Swaelmen, M. and Ting, Y. S.
- author collaboration
- organization
- publishing date
- 2019
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Methods: data analysis, Methods: numerical, Stars: binaries: close, Stars: binaries: spectroscopic, Techniques: radial velocities, Techniques: spectroscopic
- in
- Memorie della Societa Astronomica Italiana - Journal of the Italian Astronomical Society
- volume
- 90
- issue
- 3
- pages
- 13 pages
- publisher
- Italian Astronomical Society
- conference name
- EWASS 2019: Special Session 22 Stellar Multiplicity in the Gaia Era: Where do we Stand?
- conference location
- Lyon, France
- conference dates
- 2019-06-25
- external identifiers
-
- scopus:85108916159
- ISSN
- 1824-016X
- language
- English
- LU publication?
- yes
- id
- 0ca53b83-58e7-404c-8765-f20c99025d72
- date added to LUP
- 2021-08-19 11:08:36
- date last changed
- 2024-03-23 08:37:45
@article{0ca53b83-58e7-404c-8765-f20c99025d72, abstract = {{<p>We briefly review the various machine learning methods and discuss how they can be used in efficient identification and analysis of spectroscopic binary stars. They can be treated as complementary to conventional methods, and we argue that some amount of human oversight is always needed and in fact highly beneficial when employing machine learning. We propose that a general dimensionality reduction technique can serve to diagnose and classify a given data set, and in case of GALAH spectra, our method quite effectively reveals a population of SB2 and SB3 systems. Once identified, the binary spectra can be analysed with the help of generative models, which can be constructed using machine learning techniques such as The Cannon and The Payne. Furthermore, in the case of spectroscopically unresolved multiple stars, we can recover the multiple contributions to an observed spectrum by reversing the process and proceeding from analysis to identification.</p>}}, author = {{Traven, G. and Čotar, K. and Merle, T. and van der Swaelmen, M. and Ting, Y. S.}}, issn = {{1824-016X}}, keywords = {{Methods: data analysis; Methods: numerical; Stars: binaries: close; Stars: binaries: spectroscopic; Techniques: radial velocities; Techniques: spectroscopic}}, language = {{eng}}, number = {{3}}, pages = {{327--339}}, publisher = {{Italian Astronomical Society}}, series = {{Memorie della Societa Astronomica Italiana - Journal of the Italian Astronomical Society}}, title = {{Machine learning techniques meet binaries}}, volume = {{90}}, year = {{2019}}, }