Anguilla - Deep South
Part of the regional summary: Anguilla
More about this place: Anguilla on Wikipedia
More info
Leeward Caribbean Islands (NOAA CRW virtual station) · Eastern Caribbean ecoregion mean=13.1°C-heating weeksA quiet, low-relief hardbottom reef of scattered boulder and brain coral heads over red coralline algae, with an invasive lionfish tucked near the sponges - a slower counterpart to Anguilla's better-known walls. A blind Claude computer-vision point count puts coral cover around 6.6%.
One independent survey station shown with the program’s logo — click one to see how far it is from this site.
One other CRD dive site within 5 km shown in orange — click a marker to open its page.
15 of these 50 photographs are shown beside the text that discusses them under "Site description" below.
Site description
Setting
Deep South is a low-relief hardbottom reef of scattered coral heads and rocky ridges dropping into sandy grooves, carpeted in vivid red encrusting coralline algae (e.g., Image 7, Image 20, Image 29, Image 55).
It's a quieter, low-relief counterpart to Anguilla's better-known walls, worth a slow look rather than a fast fin.
General benthic features
Boulder corals likely Montastraea and Orbicella dome up alongside a corrugated brain coral, while clusters of mustard hill coral hug the rock (e.g., Image 2, Image 15, Image 16, Image 25, Image 48).
Erect brown tube sponges and wiry black sea rods add vertical texture, and an orange cushion star and banded spiny lobsters share the ledges (e.g., Image 18, Image 31, Image 54).
Coral cover
Coral cover: 6.6% — a blind Claude computer-vision point count of 63 of Anderson's unedited photographs (20 points per photo; water, fish, and obstructions excluded). Other computer-vision methods are listed in the method table.
Stressors
No corallivores evident.
Fish and other fauna
A camouflaged lionfish — an unwelcome Indo-Pacific invader now well established through the Caribbean — rests near the sponges, while a lone barracuda hangs in open water and a spotted reef fish glides past (e.g., Image 1, Image 21, Image 44).
Comparisons with other data
No independent survey was made at this exact site; the nearest ones are listed in the table below.
CV model comparison
More info
DINOv3 and CoralSCOP were run on the same photos and are listed for comparison. Coralscapes v2 and v1 were also run but are not shown: Anderson does not consider Coralscapes reliable for these photos. No diver transect exists for this trip, so agreement between the rows is not accuracy, and as of September 2026 no computer-vision method estimates coral cover accurately on new images; treat every row as indicative.| Method | Hard-coral cover (%) |
|---|---|
| In-house DINOv3 | 13.3 |
| CoralSCOP unedited | 20.5 |
| Claude | 6.6 |
Independent surveys nearby
Within 5 km, 1 independent survey station recorded hard coral cover in 2013. The most recent nearby survey is from 2013, so these values predate recent heat stress. This site's own estimate (6.6%) is indistinguishable from the range of these surveys (2.7%): the 3.9-point gap is inside the ±7 percentage-point noise between methods; the methods differ, so the comparison is context, not a like-for-like test.
Collected by other programs using different methods (the XL Catlin Seaview Survey uses photo-transects with automated image annotation), so these are context for the figures above, not a like-for-like comparison. Where a station was surveyed more than once the range is shown. Station names are not dive-site names.
| Agency | Site / location | Date | Hard coral cover (%) | Distance | Link |
|---|---|---|---|---|---|
| XL Catlin Seaview Survey | transect 25024 | 2013 | 2.7% | 3.47 km | — |
Data & links
All images from Coral Reef Diagnostics. Data are from Coral Reef Diagnostics and the organizations named in the data-sources table above.
© Coral Reef Diagnostics.