Cited by 3Astro and Planetary ScienceSpace Satellite Systems and ControlStellar, planetary, and galactic studies

AI-enhanced Citizen Science Discovers Cometary Activity on Near-Earth Object (523822) 2012 DG61

Open access
Chandler, Colin Orion, Sedaghat, Nima, Oldroyd, William J., Frissell, Maxwell K., Trujillo, Chadwick A., Burris, William A., Hsieh, Henry H., Kueny, Jay K. +16 more·2025·Research Notes of the AAS

Abstract

Abstract We report the discovery of cometary activity in the form of a pronounced tail emanating from Near-Earth Object (523822) 2012 DG61, identified in UT 2024 April 18 Dark Energy Camera images by our AI assistant TailNet. TailNet is an AI designed to filter out images unlikely to show activity for volunteers of our NASA Partner “Active Asteroids” Citizen Science campaign, from which our AI is trained. Subsequently, our archival investigation revealed 2012 DG61 is recurrently active after we found it displaying a pronounced tail in a UT 2018 April 16 Steward Observatory Bart Bok 2.3 m telescope image and UT 2018 May 14 observations by G. Borisov with the 0.3 m telescope at MARGO Observatory. Our dynamical integrations reveal that 2012 DG61, an Apollo dynamical class member, is likely in 2:1 mean-motion resonance with Jupiter. We encourage additional observations to help characterize the activity morphology of this near-Earth comet.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3847/2515-5172/ada368

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The most common way of integrating AI in citizen science is by having participants train algorithms.

    “Among citizen science projects, the most common way of integrating AI is by having participants train algorithms (Chandler et al., 2025;DeSpain et al., 2024;Duerinckx et al., 2024, p. 3;Jia et al., 2025;See et al., 2025).”

    From Deepfakes, Democracy, and the Ethics of Synthetic Media: A Synthesis of the SOLARIS Project (2026) · cites this paper as Chandler et al., 2025

    The Methods section (page unavailable) describes volunteers classifying images and the development of the TailNet AI assistant; the paper also states that the AI is trained from the citizen-science campaign. This supports an example of participant contributions used to train AI, but the paper does not say this is the most common way AI is integrated into citizen science projects. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Chandler, C. O., Sedaghat, N., Oldroyd, W. J., Frissell, M. K., Trujillo, C. A., Burris, W. A., Hsieh, H. H., Kueny, J. K., Farrell, K. A., Borisov, G. V., DeSpain, J. A., Bernardinelli, P. H., Kurlander, J., Magbanua, M. J. M., Sheppard, S. S., Mazzucato, M. T., Bosch, M. K. D., Shaw-Diaz, T., Gonano, V., Lamperti, A., da Silva Campos, J. A., Goodwin, B. L., Terentev, I. A., & Dukes, C. J. A.
Affiliations
  • University of Washington (US)
  • Northern Arizona University (US)
  • Planetary Science Institute (US)
  • U.S. National Science Foundation (US)
  • Lomonosov Moscow State University (RU)
  • University of California, San Francisco (US)
  • Carnegie Institution for Science (US)
  • Royal Astronomical Society (GB)
Corresponding author
  • Chandler, Colin Orion
  • Sedaghat, Nima
  • Oldroyd, William J.
  • Frissell, Maxwell K.
  • Trujillo, Chadwick A.
  • Burris, William A.
  • Hsieh, Henry H.
  • Kueny, Jay K.
  • Farrell, Kennedy A.
  • Borisov, Gennady V.
  • DeSpain, Jarod A.
  • Bernardinelli, Pedro H.
  • Kurlander, Jacob
  • Magbanua, Mark Jesus Mendoza
  • Sheppard, Scott S.
  • Mazzucato, Michele T.
  • Bosch, Milton K. D.
  • Shaw-Diaz, Tiffany
  • Gonano, Virgilio
  • Lamperti, Al
  • Goodwin, Brian L.
  • Terentev, Ivan A.
  • Dukes, Charles J. A.
Venue
Research Notes of the AAS
Published
2025-01-03
Volume
9
Issue
1
Pages
3
ISSN
2515-5172 (ISSN-L)
OpenAlex
W4406098859
Cited by
2
References
12
Citations by year
2026: 2
FWCI
0.89
Type
journal article
Language
en
Open access
Locations
Research Notes of the AAS (publishedVersion, cc-by)
Topics
  • Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Astro and Planetary Science
  • Physical Sciences › Engineering › Aerospace Engineering › Space Satellite Systems and Control
  • Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Stellar, planetary, and galactic studies
Keywords
near-Earth objects, cometary activity, citizen science, Dark Energy Camera

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review