Coral Reef Diagnostics

Indonesia - Halmahera: Siko Tanjung

⬇ Download this page as a report card
05
Photo: Anderson Mayfield/Coral Reef Diagnostics
Country
Survey date(s)
2026-08-15
Coordinates
0.1461, 127.1126
Coral cover
41%
Claude computer vision (143 photos) · other methods below
Observations
bleachingmortalitypredation
Heat stress
Today’s heat load
16 Sep 2026 · No heat stress
5-year thermal stress load
5-year mean max. degree heating weeks (DHW)
2021–2025
NOAA Coral Reef Watch — North Maluku 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 (NOAA CRW virtual station)
Photographs
52
Site summary
Read this summary in:

Siko Tanjung is an extensive branching Acropora reef flat worked in bad visibility and strong current, built partly on large tracts of old dead, coralline-overgrown staghorn framework that the living thicket now grows through. A handful of massive colonies are stark chalk-white against normally pigmented neighbors, worth flagging as a possible bleaching signal. A blind Claude computer-vision point count puts coral cover around 41%.

Max. depth dived
17.3 m
dive-log maximum

Two independent survey stations 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.

26 of these 52 photographs are shown beside the text that discusses them under "Site description" below.

510121415171922232427283031323536373941474850515455

Photo credit & attribution

Site description

Setting

Siko Tanjung is a broad, gently domed reef top worked in the conditions Anderson's field note records: “bad visibility and fought strong currents for much of the dive.” The imagery carries that plainly — most wide frames are hazy and blue-flat, with the far side of each bommie already lost in suspended particles, and divers appear repeatedly hanging in current above the reef (e.g., Image 7, Image 20, Image 25, Image 33, Image 40, Image 46).

General benthic features

What the site actually holds is a very extensive branching Acropora reef flat: acre-scale staghorn and bottlebrush thicket in dusty pink, lavender, and olive, running unbroken through dozens of frames (e.g., Image 2, Image 6, Image 34, Image 45, Image 49, Image 53).

Standing above it are big flat-topped tabulate Acropora plates, some over a meter across, digitate and corymbose colonies, foliose plates, brown Lobophytum, and Sinularia leathers, and a scatter of massive Porites and one textbook meandroid brain coral (e.g., Image 1, Image 3, Image 9, Image 11, Image 21, Image 26, Image 38, Image 42, Image 43).

Coral cover

Coral cover: 41% — a blind Claude computer-vision point count of 143 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

Two things stand out beyond the composition. First, large tracts of the flat are dead standing and broken staghorn framework, bleached-out skeleton overgrown by pink and magenta coralline algae and green turf (clearest in four frames), interleaved with the living thicket — an old mortality event that the reef is still built on (e.g., Image 4, Image 13, Image 44, Image 52).

Second, a handful of massive colonies are stark chalk-white while every neighbor holds normal color, one of them photographed three times (e.g., Image 8).

Fish and other fauna

A cushion star, Culcita novaeguineae, sits on the rubble beside two small snow-white branching colonies.

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

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 DINOv330.5
CoralSCOP unedited32.3
Claude41.3

Independent surveys nearby

Within 5 km, 2 independent survey stations recorded hard coral cover in 2024. Surveys since 2021 average 37% (range 25–50%, n=2). This site's own estimate (41%) sits within the recent range (25–50%); the methods differ, so the comparison is context, not a like-for-like test.

Collected by other programs using different methods (MERMAID is a data platform: each MERMAID row names the organization that did the survey, and its method is in the row's hover text), 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.

Independent survey data near this site
AgencySite / locationDateHard coral cover (%)DistanceLink
WCS Indonesia via MERMAIDInti Siko202425%0.00 kmAdiyoga D, Cholic O, Gunawan I, Rayhan A, Sutanto S, Syah L, Zulfikri M. 2024. Guraici MPA 2024. MERMAID
WCS Indonesia via MERMAIDInti Gafi202450%3.69 kmAdiyoga D, Cholic O, Gunawan I, Rayhan A, Sutanto S, Syah L, Zulfikri M. 2024. Guraici MPA 2024. MERMAID

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.