Coral Reef Diagnostics

Triton Bay - Seruanus

⬇ Download this page as a report card
05
Photo: Anderson Mayfield/Coral Reef Diagnostics
Country
Survey date(s)
2018-10-14
Coordinates
-3.8500, 134.1000
Coral cover
9.1%
Claude computer vision (66 edited photos) · other methods below
Observations
not yet tagged for this site
Heat stress
Today’s heat load
16 Sep 2026 · Bleaching Watch
5-year thermal stress load
5-year mean max. degree heating weeks (DHW)
2021–2025
NOAA Coral Reef Watch — West Papua virtual station
i 5-year mean max. DHW is the mean of the annual maximum DHWs over the five complete years named above, not conditions today.
More infoWest Papua (NOAA CRW virtual station)
Photographs
17
Site summary
Read this summary in:

Seruanus is a soft-coral-dominated site on the back side of Little Komodo Island, shaped by high flow, turbidity, and nutrient-rich, occasionally upwelling cold water; stony corals were sparse before 10 m, though healthy Acropora and massive corals up to 3-4 m appeared in the shallows. A blind Claude computer-vision point count puts coral cover around 9.1%.

Max. depth dived
18.0 m

Four other CRD dive sites within 5 km shown in orange — click a marker to open its page.

4 of these 17 photographs are shown beside the text that discusses them under "Site description" below.

16Photo: Pierre7Photo: Pierre8Photo: Pierre9Photo: Pierre10Photo: Pierre11Photo: Pierre12Photo: Pierre13Photo: Pierre14Photo: Pierre15Photo: Pierre16Photo: Pierre17Photo: Pierre

Photo credit & attribution

Site description

Setting

Poor visibility: 7-10 m max with medium, variable current, occasionally with upwelling of cold (24C) water. Proper upwelling? Site appears to be more conducive to soft coral growth: high flow, high turbidity, nutrient-rich seawater (e.g., Image 2).

General benthic features

Low cover of stony corals before 10 m (e.g., Image 3).

Soft corals impressive at all locations within site (back side of Little Komodo Island). Corals do not appear to have ever been common here before 7 m, though all substrate from base of island to 20 m was potentially of biological origin. High biodiversity of soft corals: gorgonians, encrusting soft corals (like in Balicasag), essentially every type of soft coral, sea whips (e.g., Image 4).

Acropora colonies healthy and fairly common at 5-6 m, though still not a major reef builder. Some massive corals growing up to 3- to 4-m in diameter. Unsure of species (separated corallites). Only one pocilloporid (P. verrucosa?) seen (very dark pigmentation). Reef strikingly colorful in 1-6 m, with corals growing to just below surface (e.g., Image 5).

Corals evident from dive boat.

Coral cover

Coral cover: 9.1% — a blind Claude computer-vision point count of 66 of Anderson's edited photographs (20 points per photo; water, fish, and obstructions excluded). Other computer-vision methods are listed in the method table. For pics, see “Triton Bay dive 1: Little Komodo”.

Stressors

No crown-of-thorns starfish (COTS) or other corallivores evident.

Fish and other fauna

Interesting marine life: white nudibranch (see pic), strange sea cucumber (see pic; see cucumbers relatively common.), Plerogyra (rare), some encrusting sponges, barrel sponges less common, evidence of overfishing, though occasionally some large snapper and angelfish. A nudibranch-like sea cucumber (yellow; see pics) was common at site (never before seen).

Comparisons with other data

No prior survey data from this site. If you would like to share yours, please email us.

Dive record

Dive 1: “Seruanus:” The first dive of the Triton Bay-Raja Ampat trip.

CV model comparison

As of September 2026 no computer-vision method estimates coral cover accurately on new images, so treat this as indicative rather than a measurement; it is revised as the methods improve.
Headline: Claude computer vision — a blind point count of this site's own photographs (Anderson, 2026-09-27: Claude CV is the main coral-cover value).
More infoDINOv3 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.
MethodHard-coral cover (%)
In-house DINOv318.7
CoralSCOP edited30.6
Claude (edited photos)9.1

Data & links

Images 6–17: Pierre; all other images from Coral Reef Diagnostics. Data are from Coral Reef Diagnostics.

© Coral Reef Diagnostics.