Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks

Zoe L. de Beurs*, Andrew Vanderburg, Christopher J. Shallue, Xavier Dumusque, Andrew Collier Cameron, Lars A. Buchhave, Rosario Cosentino, Adriano Ghedina, Raphaëlle D. Haywood, Nicholas Langellier, David W. Latham, Mercedes López-Morales, Michel Mayor, Giusi Micela, Timothy W. Milbourne, Annelies Mortier, Emilio Molinari, Francesco Pepe, David F. Phillips, Matteo PinamontiGiampaolo Piotto, Ken Rice, Dimitar Sasselov, Alessandro Sozzetti, Stéphane Udry, Christopher A. Watson

*Corresponding author for this work

    Research output: Contribution to journalJournal articleResearchpeer-review

    86 Downloads (Pure)


    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.
    Original languageEnglish
    Article number49
    JournalAstronomical Journal
    Issue number2
    Number of pages21
    Publication statusPublished - 2022


    • Exoplanet astronomy
    • Radial velocity
    • Convolutional neural networks


    Dive into the research topics of 'Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks'. Together they form a unique fingerprint.

    Cite this