Coral Cover: Oman 2024

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: Oman 2024

7 sites · 660 photos

Gold standard = published values (Platax 2025, Table 1) from 660 CoralNet-annotated photos. CoralSCOP ran on both edited and unedited photos (separate columns).

Site	Date	Headline (site page)	Claude	Gold standard	CoralNet	DINOv3	Coralscapes v1	Coralscapes v2	CoralSCOP unedited	CoralSCOP edited	Mean ± SD of CV	Range
Cave Site	2024-05-20	51%published point count	70^hn=15	51^a,i,jn=170	49^c,jn=106	31^dn=151	50^en=171	50^en=171	49^gn=149	51^gn=149	50 ± 13.7	31–70
Novice Bay	2024-05-20	39%published point count	42^hn=15	39^an=135	—^c,l	23^dn=120	47^en=135	48^en=135	46^g,mn=111	47^g,mn=111	40 ± 11.3	23–47
Cat Island	2024-05-21	25%published point count	36^hn=15	25^a,bn=81	25^c,bn=81	25^dn=71	34^e,fn=80	34^e,fn=80	33^gn=70	36^gn=70	33 ± 5.4	25–36
Jissah Point	2024-05-21	33%published point count	26^hn=15	33^a,bn=61	33^c,bn=61	16^dn=54	32^en=61	32^en=61	35^gn=54	38^gn=54	29 ± 9.9	16–38
Daymaniyat 1	2024-05-25	42%published point count	51^hn=15	42^a,bn=79	42^c,bn=79	34^dn=56	27^en=79	30^en=79	23^gn=56	25^gn=56	33 ± 12.9	23–51
Daymaniyat 2	2024-05-25	38%published point count	49^hn=15	38^a,bn=106	38^c,bn=106	47^dn=84	40^en=106	37^en=106	42^gn=81	50^gn=81	47 ± 3.7	42–50
Daymaniyat 3	2024-05-25	33%published point count	34^hn=13	33^a,k,bn=28	33^c,bn=28	34^dn=18	20^en=28	27^en=28	18^gn=19	13^gn=19	25 ± 10.9	13–34
All sites (unweighted mean)		—	44	37	—	30	36	37	35	37	37 ± 5.8	30–44

Notes for Oman 2024 (17)

[a] Gold standard = Mayfield AB (2025) Platax 22:27-44, doi:10.29926/platax.202512_22.0003, Table 1 (p. 31), 'Coral cover (%)', printed verbatim; n = # photos in Table 1. Denominator (Methods, p. 32): hard coral relative to the BENTHIC part of the image only - water and fish removed, unknown points kept (coral / (30 - WATER - FISH)). The manuscript's per-photo file reproduces all seven means under this rule (and 37.3 +/- 8.3 across sites, p. 37).
[b] Gold standard here is NOT manually annotated in CoralNet: every frame at this site carries CoralNet robot labels (CoralNet export; only the author's own 135 Novice Bay and 65 Cave Site frames are manually annotated in CoralNet). The CoralNet cell is therefore the SAME measurement and is excluded from the CV mean.
[c] CoralNet = CoralNet's own classifier labels only (annotator 'robot' in the point export), same denominator as the gold standard.
[d] DINOv3: site-level file of record only; the per-image output no longer exists, so its denominator is unrecorded and the value cannot be audited. DINOv3 is not used in future runs. The Cat Island value equalling the gold standard (24.9) is a coincidence - the file predates the corrected gold standard.
[e] Coralscapes (v1 EPFL-ECEO/coralscapes-vit-b-dpt; v2 coralscapesv2-dinov3-vitb-lora-dpt), run 2026-09-18 on UNEDITED originals: hard-coral AREA / WHOLE frame (water, fish, background left in the denominator - different from the gold standard). Not considered reliable for these photos; shown, never averaged. Source: the Coralscapes v1/v2 run notes.
[f] Cat Island Coralscapes n = 80: one annotated frame could not be assigned a site in that run.
[g] CoralSCOP = sum of colony-mask AREA fractions per frame (whole frame in the denominator; not a point count - denominator differs from the gold standard). Edited and unedited are PAIRED: only frames scored in both runs.
[h] Claude = blind point calls on the EDITED photos, 30 points per frame, same denominator as the gold standard (Unk in, water/fish out); mean of per-frame cover (the gold standard's aggregation). Only 15 frames per site (13 at Daymaniyat 3): thin.
[i] Table 1 prints n = 170; 171 frames are on disk and in the per-photo file (reproduces 51.4 exactly).
[j] Gold standard partly manually annotated in CoralNet: 65 of the site's frames carry the author's own points, the other 106 are CoralNet robot labels; the CoralNet cell uses only those 106 robot frames, so it is a real (partly independent) comparison.
[k] Table 1 prints the Daymaniyat 3 SD as '4.' (typo). The per-photo file gives 23.7 (23.75).
[l] Blank: every Novice Bay frame was manually annotated in CoralNet by the author, so CoralNet produced no robot label there.
[m] Novice Bay CoralSCOP = the finished edited run (111 paired frames).
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