Shaded value = in the CV mean (shade deepens with cover) Gray italic = shown for comparison but left out of the CV mean: the gold standard (the reference value) and the manually annotated in CoralNet CoralNet benchmark annotations (reference values, not models), Coralscapes (not trusted), and any value that reuses the reference's own data n = frames behind the value — = not run or not applicable (see each region's notes) Site names and method names link out (new tab)

Coral Cover: Dry Tortugas 2021

4 sites · 229 photos

Agency survey column = each site's headline: NOAA NCRMP ReefBudget 2024 at Bird Key Reef (6 fixed transects), FWC DTCREMP 2021 permanent stations elsewhere. Claude and CoralSCOP ran on the author's June 2021 photos (comparison only).

SiteDateHeadline (site page)ClaudeAgency survey (headline)CoralSCOP uneditedCoralSCOP edited
Bird Key Reef, Dry Tortugas2021-06-25–285.1%transect28e,fn=1235.1an=6—b42c,dn=114
White Shoal, Dry Tortugas2021-06-263.3%transect26e,fn=553.3an=422c,dn=35—g
Black Coral Rock, Dry Tortugas2021-06-2812%transect18e,fn=2512an=435c,dn=15—g
Texas Reef, Dry Tortugas2021-06-286.8%transect21e,fn=266.8an=4—b39c,hn=26
All sites (unweighted mean)—236.9——
Notes for Dry Tortugas 2021 (12)
  • [a] Agency survey, the site headline: Bird Key Reef = NOAA NCRMP ReefBudget 2024, 6 fixed transects (NCEI 0311367); other sites = FWC DTCREMP 2021 permanent stations. n = transects / stations, not photos.
  • [b] Not run on unedited photos at this site.
  • [c] CoralSCOP = per-frame sum of colony-mask area fractions (zero-filled; overlapping masks double-count), averaged over frames with an ok row. Area index, not a point count: denominator differs from any point-count reference. It is also unstable frame to frame (the same subject has scored 94.1% in one photo and 23.3% in another), and the mask sum overstates cover most on the healthiest reefs.
  • [d] CoralSCOP v2 (mask-sum), a folder-level run on Anderson's June 2021 dive folders: not frame-matched to the Claude photos (n = that run's frames). Comparison only.
  • [e] Claude = blind 7-call point count on the EDITED photos (20 points per photo, (HC+BL)/(20 − WATER − FISH − OBST), unknown points kept in the denominator); value = the site's headline as printed on its page.
  • [f] At Dry Tortugas the Claude value is a comparison only (survey headline); the high values reflect colony-focused photo selection.
  • [g] Not run on edited photos at this site.
  • [h] CoralSCOP here = the site page's frame-matched row: run on exactly the photos behind the Claude cell (per-frame values joined by file; capped at 100% per photo; zero-filled). Comparison only.
  • Mean/Range: Mean ± SD and Range are over the CV cells that enter the mean (CoralNet where independent, DINOv3, CoralSCOP unedited/edited, Claude). Gold standard, frames manually annotated in CoralNet, Coralscapes and same-measurement cells are shown in gray italic but never averaged.
  • Headline (site page): the coral-cover figure the site's page, report card and map pop-up print, with its method; it is never averaged into the CV mean.
  • Methods: Claude (Anthropic); DINOv3 (Meta; paper; used here as the frozen backbone of the in-house classifier); Coralscapes v1 and v2 (EPFL-ECEO; dataset paper, code); CoralSCOP (Zheng et al., CVPR 2024); CoralNet.
  • Sites: names drop the region prefix (hover for the full name) and link to the site's CRD page, or to the regional summary page where the site has none. Date = survey date from the map pins (first–last visit); sites are listed earliest first, undated sites last.

All regions