Coral Reef Diagnostics

Indonesia - Halmahera: Kusu Ridge

⬇ Download this page as a report card
05
Photo: Anderson Mayfield/Coral Reef Diagnostics
Country
Survey date(s)
2026-08-12
Coral cover
45%
Claude computer vision (249 photos) · other methods below · median 47%
Observations
None tagged; see Stressors below
Heat stress
Most recent heat load record
26 Oct 2026 · Bleaching Watch
5-year thermal stress load
5-year mean max. degree heating weeks (DHW)
2021–2025
NOAA Coral Reef Watch — North Maluku, Indonesia 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 infoNorth Maluku, Indonesia (NOAA CRW virtual station)
Photographs
253
50 shown on this page
Site summary
Read this summary in:

Kusu Ridge matches Anderson's log note exactly — epic schools of snapper and reef fish over a dim, current-worked deep pavement, finishing in near-continuous foliose plate meadows and mixed Acropora meadows in the shallows. One large plating colony is chalky white-gray against normally pigmented neighbors and may be bleached or recently dead. A blind Claude computer-vision point count puts coral cover around 45%.

Max. depth dived
33.6 m
dive-log maximum
Water temp. during survey
25–26°C
range logged on the dive
Bottom time
61 min
in at 07:25

These are unedited originals; edited versions will replace them.

This page shows 50 of the 253 photographs from this site, including every one the text cites.

44 of the 50 photographs on this page are shown beside the text that discusses them under "Site description" below.

61218192331

Photo credit & attribution

Site description

General benthic features

The deep ridge is dim, current-worked pavement crusted in coralline algae with orange, red, violet, and black encrusting sponges, gray sea fans standing off the rock, and laminar plate corals (Pachyseris-type) scattered across rubble — these are the low-cover frames, and the blue water above them carried the schooling fish the field note describes: massed yellowtail fusiliers, snapper, and clouds of anthias (e.g., Image 2, Image 14, Image 17, Image 21, Image 24, Image 28, Image 37, Image 38).

A sand-floored section holds isolated bommies, one crowned by a large table Acropora on a narrow pedestal with cardinalfish and glassfish packed beneath it. The mid-slope is the site's real signature: near-continuous foliose plating meadows running frame to frame in brown, olive, pale green-gray, and a striking violet-purple, consistent with Montipora, Echinopora, and Pachyseris, shingled over one another so tightly that little substrate is visible (e.g., Image 1, Image 9, Image 10, Image 13, Image 20, Image 22, Image 25, Image 27, Image 35, Image 40, Image 42, Image 44, Image 47, Image 49, Image 50, Image 53).

The shallows hand over to mixed Acropora — pink and mauve staghorn thickets, bright yellow-green branching stands, blue-gray corymbose colonies, Seriatopora, and Pocillopora — interleaved with the same foliose plates and worked over by chromis and damselfish (e.g., Image 3, Image 4, Image 5, Image 7, Image 8, Image 11, Image 15, Image 16, Image 26, Image 29, Image 30, Image 32, Image 36, Image 39, Image 41, Image 43, Image 45, Image 46, Image 54).

Coral cover

Stressors

One large plating colony, roughly 1.5 m across, is chalky whitish-gray against dark brown neighbors on the deep ridge and may be bleached or recently dead; most plates around it are normally pigmented (e.g., Image 34).

A few plate sections elsewhere on the slope are bare white skeleton (e.g., Image 37). The cause is not resolvable from the photographs, and no crown-of-thorns were seen in the 249 frames examined.

Comparisons with other data

We found no other surveys at this site as of 2026. If you would like to share yours, please email us.

Dive record

A deep ridge dive on 12 August 2026 run to 33.6 m at 25–26°C and finished shallow, and Anderson's field note tracks that profile exactly: "epic dive with tons of snapper and other reef fish at depth, finishing in amazing coral meadows in shallows."

CV model comparison

Mean 45%, median 47% across 249 photos.
More infoA few low-cover photos (sand, rubble, or open bottom) pull the mean down; the median is the typical photo. No computer-vision method yet 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.
More infoDINOv3 and CoralSCOP were run on the same photos and are listed for comparison. No diver transect exists for this trip, so agreement between the rows is not accuracy, and no computer-vision method yet estimates coral cover accurately on new images; treat every row as indicative.
MethodHard coral cover (%)Photos (n) ± SE
In-house DINOv342.7n = 249 · SE 1.0
CoralSCOP unedited27.6n = 249 · SE 1.2
Claude45.2n = 249 · SE 1.4

The two computer-vision methods disagree by 15.1 pp (27.6–42.7%) and read 2.5–17.6 pp below Claude's blind point count (45.2%); the headline is Claude's blind point count because no transect or manual count exists here.

Data & links

All images from Coral Reef Diagnostics. Data are from Coral Reef Diagnostics.

© Coral Reef Diagnostics.