Coral Cover: Oman 2024

Shaded value = in the CV mean (shade deepens with cover) Grey italic = shown for comparison but left out of the CV mean: the gold standard and manual CoralNet annotations (human 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	Claude	Gold standard	CoralNet	DINOv3	Coralscapes v1	Coralscapes v2	CoralSCOP unedited	CoralSCOP edited	Mean ± SD of CV	Range
Cave Site	2024-05-20	69.9n=15	51.4n=170	48.7n=106	31.2n=151	50.3n=171	50.3n=171	49.0n=149	50.5n=149	49.9 ± 13.7	31.2–69.9
Novice Bay	2024-05-20	42.2n=15	38.5n=135	—	23.0n=120	46.8n=135	47.5n=135	45.9n=111	47.3n=111	39.6 ± 11.3	23.0–47.3
Cat Island	2024-05-21	36.1n=15	24.9n=81	24.9n=81	24.9n=71	34.1n=80	34.2n=80	33.3n=70	36.5n=70	32.7 ± 5.4	24.9–36.5
Jissah Point	2024-05-21	26.3n=15	33.3n=61	33.3n=61	16.0n=54	31.9n=61	31.5n=61	34.9n=54	38.1n=54	28.8 ± 9.9	16.0–38.1
Daymaniyat 1	2024-05-25	51.2n=15	41.7n=79	41.7n=79	34.4n=56	26.6n=79	29.5n=79	23.2n=56	24.6n=56	33.4 ± 12.9	23.2–51.2
Daymaniyat 2	2024-05-25	49.3n=15	38.1n=106	38.1n=106	46.5n=84	39.5n=106	37.3n=106	42.2n=81	50.4n=81	47.1 ± 3.7	42.2–50.4
Daymaniyat 3	2024-05-25	33.8n=13	33.0n=28	33.0n=28	34.2n=18	20.3n=28	27.0n=28	17.6n=19	13.3n=19	24.7 ± 10.9	13.3–34.2
All sites (unweighted mean)		44.1	37.3	—	30.0	35.6	36.8	35.2	37.2	36.6 ± 5.8	30.0–44.1

Notes for Oman 2024 (16)

[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, Unk kept (coral / (30 - WATER - FISH)). The manuscript's own 'Oman photo by photo.csv' 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 Novice Bay 135 + 65 Cave Site frames are Anderson's own). 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 (oman_cover_by_site_20260807.csv); the per-image output no longer exists, so its denominator is unrecorded and the value cannot be audited. Anderson has retired DINOv3 from 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 trusted (Anderson); shown, never averaged. Source: CORALSCAPES_V1_V2_UNEDITED_20260918.md.
[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 (sheet-B display), 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. The CSV also carries the pooled value, the gold standard recomputed on the same frames, and the UNEDITED sheet-B fair test re-scored on the gold-standard denominator.
[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 are Anderson'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); earlier tables carried 23.7 as if published.
[l] Blank: every Novice Bay frame was manually annotated in CoralNet by Anderson, so CoralNet produced no robot label there. The old 38.6 (n=114) has no traceable source.
[m] Novice Bay CoralSCOP changed from 38.2/41.0 (66 paired frames, 2026-08-24, edited run then incomplete) to 45.9/47.3 (111 paired frames, finished edited run).
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 but never averaged (*).
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