### BIPB71 — Peros Banhos
**CRD page:** [Peros Banhos Coral Surveys (16–17 Apr 2015)](https://coralreefdiagnostics.com/peros-banhos-20150416-to-0417)

**17 Apr 2015**
**GPS:** 5.25511°S, 71.81393°E
**Setting:** protected emergent channel reef, 18 m
**Coral cover:** 63.1% (9 formal transects, D3–D4; **algal cover 21.6%**) · **published image bleaching:** the `Mean(%bleaching)` cell is blank for this site — no value exists, and none may be inferred
**Live hard coral cover across methods:** formal transects 63.1% · CoralNet points — none · Coralscapes masks — none. **No imagery exists for BIPB71, so neither computer-vision product was ever generated and no multi-method comparison is possible here.** Where those products do exist elsewhere in Chagos they carry different sampling footprints and denominators from the transects and should not be averaged with them; at this site the transect figure stands alone.
**Temperature:** 30.6 °C · **Salinity:** 34.4
**Photo review:** **none — no photographs exist for this site anywhere.** **Anderson did not dive here, and the CRD Peros Banhos page gives the reason without varnish: "Did not dive because the dive boat left without me (not the first time this happened!)."** The published site table's `submitted to CoralNet?` column reads **"no photos"**, and the supplement's `formal vs. informal comparison` sheet records the same outcome as **"formal surveys only"**. No folder resolves to site number 71 under any prefix or casing; the site returns zero photo directories and zero frames. **Everything below therefore rests on transect point counts alone, and reef condition at BIPB71 cannot be assessed** — bleaching, tissue loss, disease, predation scarring, COTS, fish and macrofauna are all simply *unavailable*, and must never be read as zero or inferred from neighbouring Peros Banhos sites. **That matters more at this site than at any other in this group, because BIPB71 carries the survey's fourth-highest dead-coral reading and there is no imagery to say why.**

**This is one of the highest-cover reefs in the entire survey, and nobody photographed it.** At **63.1% coral cover BIPB71 ranks 6th of 109 Chagos sites** — behind BISP96 (85.98%), BIPB72 (72.35%), BISA98 (71.0%, also in this pass), BITB58 (67.0%) and BIPB69 (64.73%) — and third of the twenty Peros Banhos sites, against an island mean of 46.6%. **Algal cover of 21.6% ranks 106th of 109 — fourth-lowest in the archipelago** — for a coral-to-algae ratio of 2.92. Bare substrate is 7.63% and non-coral invertebrates 7.75%. Nine formal transects give a raw mean of 62.33% ± 12.64 SD over a **40–84% range**: high-cover at every single transect, none below 40%, which is a genuinely unusual consistency for a Chagos site. It is marked **`Validation`** in the published table (Validation = 1), one of 37 so assigned.

**BIPB71 is an *Acropora* reef and very little else.** All values below are **percent of total benthos, not percent of coral**, and the 11 genus columns sum to exactly 63.06%, matching the published cover figure. ***Acropora* alone is 46.19% of the benthos — 73.2% of all live coral*** — with ***Porites* 11.38% (18.0%)** a distant second. The remaining nine genera together make up under 9% of the coral: *Pocillopora* 2.00%, *Favia* 1.63%, *Pavona* 0.63%, *Montipora* 0.56%, *Platygyra* 0.25%, *Ctenella* 0.19%, *Millepora* 0.13%, *Stylophora* 0.06% and *Symphyllia* 0.06%. **Genus count of 11 is 105th of 109 sites** — near the bottom of the archipelago — and the indices confirm how lopsided that is: H′ = 0.89, Simpson = 0.43, **evenness J′ = 0.37, the lowest of the seven photo-less sites and one of the most one-sided assemblages in the survey.** Very high cover on very few genera.

**The depth profile cannot really be tested at this site, and what little there is turns on a single transect.** D3 (8 transects) averages 62.13% coral against 29.13% algae; D4 (1 transect) reads 64.00% against 14.00%. The two-point cover difference is meaningless beside the 40–84% spread within D3 alone, and **the site is effectively single-depth: eight of the nine transects sit in D3.** What the numbers do show is a compositional shift, though on one deep transect it is indicative only. **At D3 *Acropora* holds 50.38% of the benthos — 81% of the stratum's coral — across 11 genera**, with *Porites* only 5.75%, *Pocillopora* 2.00%, *Pavona* 1.25% and *Montipora* 1.12%. **At D4 *Acropora* falls to 42.00% while *Porites* triples to 17.00%**, and the stratum resolves **only four genera in total** (*Acropora*, *Porites*, *Favia* 3.00%, *Pocillopora* 2.00%). The algal budget shifts with it: plain turf collapses from 18.25% at D3 to 4.00% at D4, sediment-laden turf from 3.00% to exactly zero, while erect algae rises from 0.25% to 4.00% and bare substrate from 3.25% to 12.00%. Crustose coralline algae is flat at 5.00% in both. **All of the D4 side of that comparison is one 100-point transect** (see Flag 3).

Site-wide the algal composition is unusual for Chagos: **plain turf dominates at 11.13% — 52% of all algae, and 46th of 109 sites — while crustose coralline algae is only 5.00%, 102nd of 109 and among the lowest CCA readings in the archipelago.** Sediment-laden turf is 1.50%, a fifth of the dataset mean of 7.37%, as a flushed channel setting should read; erect algae 2.13%, macroalgae 1.75%, cyanobacteria 0.06%. Across the nine transects, pavement averages just 13.44% — the lowest of the seven photo-less sites, because coral has taken the space — with sand 3.33% and rubble 2.89%.

**The mortality signal is the second story here, and it is not small.** Dead coral averages **15.67% across the nine transects — the fourth-highest site value of the 109, against a dataset mean of 4.56%** — with a 0–35% range and two transects at 31% and 35%. **Recently dead coral averages 2.0%, with one transect (`BIPB71_d3_T4`) reading 12%.** A reef with cover this high should not also be among the most dead-coral-laden in the survey. Without imagery there is no way to tell whether that standing dead material is storm or predation damage, an *Acropora* die-back in progress, or simply the skeleton that a dense tabular *Acropora* stand always carries beneath it. **It is the one thing at this site that the available data cannot resolve, and the one that most needed a photograph.**

<b>Assemblage composition.</b> Nine transects across two strata give 63.1% coral against 21.6% algae on 11 nonzero genera, overwhelmingly *Acropora* (46.19% of benthos, 73.2% of coral) with *Porites* second (11.38%, 18.0%) and nothing else above 2%. Cover is 6th of 109 and algal cover 106th of 109, on a turf-dominated, CCA-poor, sediment-free floor consistent with a flushed channel setting; evenness of J′ = 0.37 makes it one of the most one-sided assemblages in the archipelago. Eight of nine transects sit in D3, so the depth profile is untestable, and mean dead coral of 15.67% — 4th of 109 — sits unexplained beside the high cover. **There is no photographic record whatsoever, so none of this can be corroborated visually and no statement about the reef's condition — bleaching, mortality cause, disease, predation or fauna — is possible at BIPB71.**

**Flags:** (1) **NO PHOTOGRAPHS EXIST AND ANDERSON DID NOT DIVE HERE** (the dive boat left without him). Zero photo directories resolve to site number 71; `submitted to CoralNet?` reads "no photos"; the comparison sheet reads "formal surveys only". There are consequently no CoralNet points, no Coralscapes masks, no multi-method comparison, and **no basis for any condition assessment** — bleaching, disease, predation, COTS and fauna are unavailable, not zero. (2) **⚠️ HIGH DEAD CORAL, CAUSE UNRESOLVABLE.** Mean dead coral 15.67% — **4th of 109 sites**, against a dataset mean of 4.56% — with transects spanning 0–35% and recently dead reaching 12% on one transect. **Anderson's judgement needed** on whether this reads as *Acropora* die-back, physical damage, or the normal standing skeleton of a dense tabular stand. This is the single finding at BIPB71 most worth acting on, and imagery would have settled it. (3) **⚠️ D4 RESTS ON A SINGLE 100-POINT TRANSECT, AND CARRIES 50% OF THE HEADLINE NUMBER.** Site cover is the unweighted mean of the two stratum means — (62.125 + 64.00) / 2 = 63.06 — so **one transect out of nine determines half the 63.1% figure that ranks this site 6th of 109.** It is also the only evidence for the D3→D4 compositional shift and for the four-genus deep stratum described above. Transect counts by stratum are D3 = 8, D4 = 1. **This is the thinnest stratum weighting of the seven photo-less sites and should be stated wherever the 63.1% is quoted.** (4) **THE SITE IS EFFECTIVELY SINGLE-DEPTH** — eight of nine transects in D3. Do not read the D3/D4 cover similarity (62.13% vs 64.00%) as an even depth profile; it is one number against eight. (5) **THE PUBLISHED `Mean(%bleaching)` CELL IS BLANK.** BIPB71 appears in `formal vs. informal comparison` only as a placeholder row keyed under `site code 2`, carrying no cover, bleaching or image count. **% bleached is unavailable and must not be computed from anything else.** Corpus-wide the published bleaching figure is a **computer-vision product** rather than an in-situ observation, with per-image human-vs-model agreement of r = 0.40 for bleached against r = 0.72 for live hard coral (`CHAGOS_MULTIMETHOD_README.md`) — but here there is no figure at all to caveat. **Note separately that the neighbouring BIPB61 carries a documented bad bleaching value (`Mean(%bleaching)` = 12.857 against 12.0 in both CoralNet runs), so Peros Banhos bleaching figures generally warrant a second look.** (6) **THE 11-GENUS RICHNESS IS PARTLY AN EFFORT ARTEFACT.** At 900 points BIPB71 has the lowest survey effort of the seven photo-less sites apart from the two single-transect sites, and recorded richness scales with effort across the archipelago. **The *Acropora* dominance at 73.2% of coral is robust; the genus count of 11 (105th of 109) is not.** (7) **CORRECTION FOR THE MASTER DOCUMENT: BIPB71 is not the second-highest-cover site in the dataset — it is sixth**, and BISA98 (71.0%) is third, not first; BISP96 (85.98%) leads. **The defensible claim is that two of the six highest-cover sites in the survey were never dived or photographed by Anderson (BISA98 3rd, BIPB71 6th)** — still the most striking thing about this group. (8) **Integrity checks pass:** the 11 genus columns sum to 63.06% against a published 63.0625%; the six algal categories sum to 21.56% against a published 21.5625%. Both reconcile exactly. (9) **All nine transects are 100-point**, so there is no point-count weighting issue within the site — but 900 points total is low, and the site-level cover figure is still an unweighted mean of two very unequally replicated strata (Flag 3). (10) Per-site workbook `BiPb71-benthic data.xlsx` is present. Depth is published as 18 m at site level but only as strata D3–D4 in the depth table — **no per-stratum metre values.**

**Benthic data:** [Download BIPB71 benthic survey data (CSV)](../benthic_data/BIPB71_benthic.csv) — scleractinian cover by genus with full names, plus substrate and algal categories (bare substrate, CCA, turf, sediment-laden turf, macroalgae, erect algae, non-coral invertebrates), from the LOF BIOT-1 survey (Mayfield & Dempsey 2026, *Oceans*, supplemental file S1).