Files in this item
Identifying exoplanets with deep learning. IV. Removing stellar activity signals from radial velocity measurements using neural networks
Item metadata
dc.contributor.author | de Beurs, Zoe. L. | |
dc.contributor.author | Vanderburg, Andrew | |
dc.contributor.author | Shallue, Christopher J. | |
dc.contributor.author | Dumusque, Xavier | |
dc.contributor.author | Cameron, Andrew Collier | |
dc.contributor.author | Leet, Christopher | |
dc.contributor.author | Buchhave, Lars A. | |
dc.contributor.author | Cosentino, Rosario | |
dc.contributor.author | Ghedina, Adriano | |
dc.contributor.author | Haywood, Raphaëlle D. | |
dc.contributor.author | Langellier, Nicholas | |
dc.contributor.author | Latham, David W. | |
dc.contributor.author | López-Morales, Mercedes | |
dc.contributor.author | Mayor, Michel | |
dc.contributor.author | Micela, Giusi | |
dc.contributor.author | Milbourne, Timothy W. | |
dc.contributor.author | Mortier, Annelies | |
dc.contributor.author | Molinari, Emilio | |
dc.contributor.author | Pepe, Francesco | |
dc.contributor.author | Phillips, David F. | |
dc.contributor.author | Pinamonti, Matteo | |
dc.contributor.author | Piotto, Giampaolo | |
dc.contributor.author | Rice, Ken | |
dc.contributor.author | Sasselov, Dimitar | |
dc.contributor.author | Sozzetti, Alessandro | |
dc.contributor.author | Udry, Stéphane | |
dc.contributor.author | Watson, Christopher A. | |
dc.date.accessioned | 2022-08-22T16:30:09Z | |
dc.date.available | 2022-08-22T16:30:09Z | |
dc.date.issued | 2022-08-01 | |
dc.identifier | 280831192 | |
dc.identifier | a2b5b1c7-a27c-48be-83db-074152f27b04 | |
dc.identifier | 85134854128 | |
dc.identifier | 000824065700001 | |
dc.identifier.citation | de Beurs , Z L , Vanderburg , A , Shallue , C J , Dumusque , X , Cameron , A C , Leet , C , Buchhave , L A , Cosentino , R , Ghedina , A , Haywood , R D , Langellier , N , Latham , D W , López-Morales , M , Mayor , M , Micela , G , Milbourne , T W , Mortier , A , Molinari , E , Pepe , F , Phillips , D F , Pinamonti , M , Piotto , G , Rice , K , Sasselov , D , Sozzetti , A , Udry , S & Watson , C A 2022 , ' Identifying exoplanets with deep learning. IV. Removing stellar activity signals from radial velocity measurements using neural networks ' , Astronomical Journal , vol. 164 , no. 2 , 49 . https://doi.org/10.3847/1538-3881/ac738e | en |
dc.identifier.issn | 0004-6256 | |
dc.identifier.other | Jisc: 444027 | |
dc.identifier.other | publisher-id: ajac738e | |
dc.identifier.other | manuscript: ac738e | |
dc.identifier.other | other: aas27921 | |
dc.identifier.other | ORCID: /0000-0002-8863-7828/work/117211242 | |
dc.identifier.uri | https://hdl.handle.net/10023/25874 | |
dc.description | Funding: This project has received funding from the European Research Council (ERC) under the European Unions Horizon 2020 research and innovation program (SCORE grant agreement No. 851555). A.C.C. acknowledges support from the Science and Technology Facilities Council (STFC) consolidated grant No. ST/R000824/1 and UKSA grant ST/R003203/1. R.D.H. is funded by the UK Science and Technology Facilities Council (STFC)’s Ernest Rutherford Fellowship (grant number ST/V004735/1). M.P. acknowledges financial support from the ASI-INAF agreement No. 2018-16-HH.0. A.M. acknowledges support from the senior Kavli Institute Fellowships. | en |
dc.description.abstract | Exoplanet detection with precise radial velocity (RV) observations is currently limited by spurious RV signals introduced by stellar activity. We show that machine-learning techniques such as linear regression and neural networks can effectively remove the activity signals (due to starspots/faculae) from RV observations. Previous efforts focused on carefully filtering out activity signals in time using modeling techniques like Gaussian process regression. Instead, we systematically remove activity signals using only changes to the average shape of spectral lines, and use no timing information. We trained our machine-learning models on both simulated data (generated with the SOAP 2.0 software) and observations of the Sun from the HARPS-N Solar Telescope. We find that these techniques can predict and remove stellar activity both from simulated data (improving RV scatter from 82 to 3 cm s−1) and from more than 600 real observations taken nearly daily over 3 yr with the HARPS-N Solar Telescope (improving the RV scatter from 1.753 to 1.039 m s−1, a factor of ∼1.7 improvement). In the future, these or similar techniques could remove activity signals from observations of stars outside our solar system and eventually help detect habitable-zone Earth-mass exoplanets around Sun-like stars. | |
dc.format.extent | 21 | |
dc.format.extent | 4664953 | |
dc.language.iso | eng | |
dc.relation.ispartof | Astronomical Journal | en |
dc.subject | Exoplanet astronomy | en |
dc.subject | Radial velocity | en |
dc.subject | Convolutional neural networks | en |
dc.subject | QA75 Electronic computers. Computer science | en |
dc.subject | QB Astronomy | en |
dc.subject | QC Physics | en |
dc.subject | DAS | en |
dc.subject.lcc | QA75 | en |
dc.subject.lcc | QB | en |
dc.subject.lcc | QC | en |
dc.title | Identifying exoplanets with deep learning. IV. Removing stellar activity signals from radial velocity measurements using neural networks | en |
dc.type | Journal article | en |
dc.contributor.sponsor | Science & Technology Facilities Council | en |
dc.contributor.sponsor | Science & Technology Facilities Council | en |
dc.contributor.institution | University of St Andrews. School of Physics and Astronomy | en |
dc.contributor.institution | University of St Andrews. St Andrews Centre for Exoplanet Science | en |
dc.identifier.doi | 10.3847/1538-3881/ac738e | |
dc.description.status | Peer reviewed | en |
dc.identifier.grantnumber | ST/R003203/1 | en |
dc.identifier.grantnumber | ST/R00824/1 | en |
This item appears in the following Collection(s)
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.