Coral Reef Diagnostics

Indonesia - Halmahera: Proco

⬇ Download this page as a report card
05
Photo: Anderson Mayfield/Coral Reef Diagnostics
Country
Survey date(s)
2026-08-13
Coral cover
32%
Claude computer vision (227 photos) · other methods below · median 29%
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
228
50 shown on this page
Site summary
Read this summary in:

Proco is a shallow, sunlit, densely coral-covered reef — Anderson stayed at 2-3 m for most of the dive for the light and the sheer diversity of scleractinians on display, from tabulate Acropora to meandroid brains to fire coral. A blind Claude computer-vision point count puts coral cover around 32%.

Max. depth dived
26.9 m
dive-log maximum
Water temp. during survey
26–27°C
range logged on the dive
Bottom time
58 min
in at 11:23

These are unedited originals; edited versions will replace them.

This page shows 50 of the 228 photographs from this site, including every one the text cites.

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

35710131426273435363738

Photo credit & attribution

Site description

Setting

A shallow, sunlit dive on 13 August 2026 at 26–27°C.

General benthic features

The dominant impression is diversity of growth form. Single frames carry corymbose and digitate Acropora in salmon, mauve, olive, and pale green, tabulate Acropora plates up to a meter or more across with crisp white growth margins, columnar and digitate Porites with rounded pale tips, gray massive Porites domes, meandroid Symphyllia- and Lobophyllia-type brains, foliose Turbinaria and Montipora whorls, Pocillopora, Millepora-type fire coral, and free-living fungiids, all within a few meters of one another (e.g., Image 1, Image 2, Image 4, Image 6, Image 8, Image 18, Image 20, Image 23, Image 25, Image 28, Image 30, Image 31, Image 32, Image 33, Image 41, Image 42, Image 46, Image 52, Image 53, Image 54).

The invertebrate background is unusually colorful: large scarlet, crimson, and orange barrel and encrusting sponges, brown and red gorgonian sea fans, purple and mauve soft corals, black-coral bushes off the drop-off, tunicates, and a blue Linckia sea star (e.g., Image 9, Image 11, Image 15, Image 16, Image 19, Image 21, Image 24, Image 29, Image 40, Image 44, Image 47, Image 49, Image 50, Image 51).

Toward the drop-off the mixed assemblage gives way to broad, near-continuous pale gray staghorn Acropora thickets blanketing the slope into blue water (e.g., Image 12, Image 22).

Coral cover

Stressors

One brain-type massive colony carries several sharply bounded white patches in the valleys between its ridges, recent mortality, cause not stated (e.g., Image 8).

Fish and other fauna

Fish were dense throughout: anthias, chromis, fusiliers, glassfish under the sponge overhangs, and butterflyfish over the crest.

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.

Other notes

The profile reached 26.9 m, but Anderson's field note explains why the imagery is overwhelmingly bright and shallow (e.g., Image 17): "stayed at 2–3 m for most of the dive since light was better and there were so many beautiful scleractinians."

CV model comparison

Mean 32%, median 29% across 227 photos.
More infoA few colony-focused photos raise the mean; 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 DINOv331.9n = 227 · SE 0.7
CoralSCOP unedited33.8n = 227 · SE 1.0
Claude32.0n = 227 · SE 1.4

The two computer-vision methods agree within 1.9 pp (31.9–33.8%) and read within 1.8 pp of Claude's blind point count (32.0%).

Data & links

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

© Coral Reef Diagnostics.