Coral Reef Diagnostics

Indonesia - Komodo NP: Padar Island (Padar Kecil)

⬇ Download this page as a report card
05
Photo: Anderson Mayfield/Coral Reef Diagnostics
Country
Survey date(s)
2019-01-23
Coordinates
-8.6550, 119.5800
Coral cover
8.1%
Claude computer vision (56 edited photos) · other methods below
Observations
shipwreck
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 — East Nusa Tenggara 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 infoEast Nusa Tenggara (NOAA CRW virtual station) · Lesser Sunda ecoregion mean=6.9°C-heating weeks
Photographs
5
Site summary
Read this summary in:

A Komodo site built around a small wrecked fishing boat, its hull fouled with turf, tunicates, and barnacles, where the 5-10 m band is almost wall-to-wall soft coral in rust, orange, olive, and lavender despite the high cover figure. Hundreds of mushroom corals were piled in the shallows, and a superbly camouflaged frogfish was photographed.

Max. depth dived
22.3 m
dive-log maximum
Water temp. during survey
26.7°Cii
-1.2°C vs the 2019 mean sea temperature (27.9°C)
ii mean of 1 logged dive(s) at "Padar Kecil" in dive_log_master_20260826.csv, joined on log_depth_basis name 20260921

Photo credit & attribution

Site description

General benthic features

The photographs are dominated by soft coral, which is worth saying plainly because this site carries a high cover figure. Two wide frames are almost wall-to-wall octocoral: rust and orange Sinularia trees, olive-green tufted soft corals, cream and lavender convoluted leathery colonies of the Lobophytum and Sarcophyton type, and rust-red nephtheids, running unbroken into blue water with only narrow white sand channels and a tan plating coral for contrast; a blue-and-yellow butterflyfish, a longnose butterflyfish, and a parrotfish are the fish in frame (e.g., Image 4, Image 5).

This is exactly the belt he logged as nearly all soft coral from 5 to 10 m, blanketing the benthos. The hard coral evidence is one close frame: a dark green branching Acropora bush with pale and bare branch tips, and immediately below it a large orange-brown mushroom coral with a pale margin - one of the hundreds of fungiids he found piled at 2-4 m - set among red sponge, magenta crustose coralline algae, and a crinoid (e.g., Image 1).

One frame is the wreck itself: a hazy view along a heavily fouled hull, uniformly coated in turf and green fouling growth with a dark hold opening, and no coral recruits visible at that scale, consistent with his note that it carried urn tunicates and barnacles but few recruits (e.g., Image 2).

Coral cover

Coral cover: 8.1% — a blind Claude computer-vision point count of 56 of Anderson's edited photographs (20 points per photo; water, fish, and obstructions excluded). Other computer-vision methods are listed in the method table.

Stressors

No bleaching or disease lesions are resolvable. No crown-of-thorns starfish (COTS) or other corallivores evident.

Fish and other fauna

The last frame is a superbly camouflaged frogfish, pink and olive mottled to match the coralline-encrusted rock it sits on, betrayed only by its mouth line (e.g., Image 3).

Comparisons with other data

Also on record for this site: Got good pictures and even a video to show how abundant they were. Flying gurnard (second of trip/life), Stylophora pistillata, sand @ 14 m (with garden eels). Small coral bommies at 15 m but mostly sand. Cool, CCA-coated scorpionfish, larval nudibranchs growing on soft coral. Plerogyra, Pachyseris, never-before-seen ascidian (colonial), first pipefish of trip, 1 Pocillopora acuta, beautiful mantis shrimp (got good pics). Also featured tunicates and damselfish nests. Fungia only hard coral common above 5 m, though some Acropora tables also present.

Dive record

One dive, 23 January 2019, 14:40, 65 minutes, max 22.3 m by his log, 25.6 degrees C, 5-10 m visibility, and weak current, on a site built around a small wrecked fishing boat.

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 DINOv324.0
CoralSCOP edited45.8
Claude (edited photos)8.1

Dive history

DateTime inMax depth (m)Bottom time (min)
2019-01-2314:4022.3—

Data & links

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

© Coral Reef Diagnostics.