Methodology
FleetEdge combines certificate data, race results, and environmental context into a consistent performance-archetype framework.
Every fleet has a fingerprint.
From the Solent to the Aegean — see how the physics plays in your waters.
Hidden ShapeThe hidden shape of the fleet.
The kinds of boat that keep appearing when every hull is measured the same way.
The shape of the fleet, before the scoreboard has anything to say.
FleetEdge's Multi-dimensional Performance Archetype Engine combines three independent data authorities into a single analytical framework. The preceding pages — Hull Efficiency, Rating & Classification, The Physics — each describe one layer of input. This page shows what happens when they converge.
Ocean and atmosphere, sampled at the race.
ERA5 Atmosphere ERA5 is the ECMWF global atmospheric reanalysis — wind, wave, pressure, and boundary-layer state on a common hourly grid, retrospectively computed against the full observation network. FleetEdge samples ERA5 at race-leg centroids and venue bounding boxes, timed to each race's actual window, and associates the atmospheric state per boat via race participation. Atmospheric enrichment is corpus-wide: every scored race carries ERA5-derived dimensions, and weather-dependent features fold into the archetype engine uniformly.
HYCOM Ocean HYCOM GLBy 93.0 is the Hybrid Coordinate Ocean Model global reanalysis at 1/12° horizontal resolution — surface currents, temperature, and sea-surface height retrospectively computed against the global ocean-observation network. FleetEdge samples HYCOM at the same race-leg centroids and venue bounding boxes as ERA5, extracting surface-current magnitude and direction timed to each boat's actual race geometry rather than to a generic venue average.
Coverage posture. ERA5 atmospheric enrichment covers the scored race set. HYCOM ocean-current enrichment focuses on the five IRC offshore classics where tidal flow is a first-order variable rather than a rounding error — Cowes, Fastnet, Rolex Middle Sea, Sydney–Hobart, and RORC Caribbean 600. Both layers fold into the unified environmental input to the archetype framework, and current-derived context is labeled where it is used. See Ocean Intelligence for the race-by-race current treatment.
The signals that describe performance.
Each boat in the fleet is described by a set of features drawn from the three data authorities — the kinds of parameters naval architects, rating engineers, and physicists use to characterize a sailing yacht's performance envelope. FleetEdge groups them into five feature families.
| Family | What it captures | Source Authority |
|---|---|---|
| Hull efficiency | Length, displacement, wetted-surface, and form indicators from rating certificates. | ORC Certificate |
| Stability | Righting-moment and angle-of-vanishing-stability indicators from rating certificates. | ORC Certificate |
| Rig performance | Sail-area and rig-proportion indicators. | ORC Certificate |
| Rating position | Corrected-time and rating-band context. | ORC Scoring |
| Physics delta | FleetEdge/SailEdge comparative performance indicators. | SailEdge vs ORC baseline |
Finding the axes that matter.
The raw signals overlap. Hull length tracks displacement; rig height tracks sail area. FleetEdge reduces the measured signals into a smaller, cleaner set of design axes — the dimensions along which boats genuinely differ from one another, stripped of correlation and noise.
Five design axes capture most of how boats differ: hull form (overall size and power), hull efficiency (how cleanly the hull moves through the water), heel sensitivity (how much realized speed depends on holding a narrow heel angle), directional bias (whether a boat is stronger upwind or downwind — its regime affinity), and platform stability (how much righting moment the boat carries relative to its displacement).
These design axes are the reduced result — distinct from the measured feature families above, which are the raw inputs before reduction. Together the axes place every boat at a specific point in a shared design space, and the eight performance archetypes are the kinds of boat that keep appearing within it.
Many signals → five stable design axes
Measure every boat the same way, and the kinds appear
FleetEdge measures every boat in the fleet the same way — from its certificate, and from the physics applied to that certificate's geometry. Compared on equal terms, the same kinds keep appearing — across regions, rating systems, and years of new certificates. The 2026 census resolves them into the eight performance archetypes — assigned before the gun. Race results and the weather they were sailed in build the evidence behind each assignment — condition fit, crew residual, validation — never the assignment itself.
Five design axes → 8 performance archetypes
The 2026 census: eight archetypes.
Special Note — the 2026 census (August 2026). Two independent developments came together this season, and together they justified a set of studies testing how the fleet actually clusters. First, the fleet itself moved: a growing majority of certificates now carry ORC VPP 2026, which includes ORC’s published, revised residuary-resistance treatment. Second, the R16.4 physics refresh brought a more accurate righting-moment (RM) calculation. Run against the VPP 2026 fleet, the census converged on eight archetypes; the VPP 2025 census had held a slightly stronger cohesion around eleven. Eight is not a redesign — it is what the 2026 measurements resolve to, and we follow the evidence. SailrScience is committed to accuracy and transparency, building on the foundational truth of the ORC Certificate.
Three structural families, eight archetypes.
Large-Platform
AEROSTREAM, AEROCORE, LEANRUN, and AEROFORCE — archetypes whose identity is set by scale above the fleet median: waterline, rig height, and wetted platform lead the structural signature. Four archetypes across six measured slots.
Compact
SPARKFLEX, KEELRUN, and LEANFORCE — archetypes whose identity is set by scale below the fleet median: shorter waterlines, smaller rigs, lighter platforms. Three archetypes across four measured slots.
Displacement-Led
HEFTLINE — the archetype whose identity is set by carried displacement rather than scale: high displacement for length, low wetted-surface ratio.
Signal strengthens with data.
Archetype identity comes from the certificate; confidence comes from the racing. A boat's archetype assignment is computed from the structural inputs of its certificate at a stated vintage, under a stated taxonomy version — race results, weather, and current data never move it. The same certificate vintage under the same model version reproduces the same assignment; a re-measured certificate or a model revision may legitimately change it, and the change is dated.
What race data builds is evidence around that fixed identity: condition fit, the Performance Potential Index, and the crew residual all sharpen as a boat accumulates observations across varied conditions. A boat with few observations has wide confidence bounds on its measured profile; a boat with many has a high-confidence profile with precisely resolved coordinates.
The methodology itself is validated against the fleet. The share of the fleet's structural signal the five design axes capture is not a target — it is a measurement of how well the structure fits the fleet.
The archetypes are not imposed — measure the fleet the same way and the same kinds keep appearing; the 2026 census resolves them to eight. As the fleet grows and new events are processed, these numbers update. The methodology is transparent and reproducible.
The white paper.
The engine behind this page — the Multi-dimensional Performance Archetype Engine — is documented publicly by SailrScience Research: what it measures, the five-axis vessel fingerprint, and how the archetypes are recovered and held stable across releases. The full white paper is available on request through the research site.
Validation evidence publishes on this site as it clears — each artifact carries its evidence badge, moving from Validation to Latest published view when a run completes. The current artifacts live on Validation Analyses.
Read the methodology at the source: The archetype model at SailrScience Research → — overview public, full white paper by request.
Three floors. Every page obeys the same rule.
Structural readouts — archetype distribution, designer or class signatures, dimension breakdowns — publish for any fleet that exists. Describing what a fleet IS requires only that it exists.
Comparative or result-ranking narratives — who finished where, which archetype performed better on this course, who closed the gap — require a sufficient number of boats. Comparison across too few boats is anecdote, not analysis.
Crew-attribution or performance-residual narratives — decomposing a result into what the boat gave and what the crew added — require a substantial number of boats within a single event. Below that, noise dominates the residual.
Cohorts below the applicable floor carry a Low-sample badge and limit themselves to the structural tier; comparative narrative is suppressed. The policy itself is the public invariant every page is measured against today.
Five public evidence badges.
Every analytical card on FleetEdge carries one of five public evidence badges — a closed, stable lexicon saying what kind of claim the figure makes. The lexicon is defined once, on the How It Works badge legend, which this anchor consumes rather than restates.
Badges say what kind of claim a figure makes; its scope label says what it counts. The cohort vocabulary behind every FleetEdge count — ORC-rated, mapped-IRC, classified, race data vs. authority counts — is defined on the Data Definitions page.
See Methodology in the Sydney Hobart fleet.
Sydney Hobart racing brings methodology into sharp relief — see how the physics meets the fleet's regime and rivalries.
Explore Sydney HobartRigorous methodology. Transparent pipeline. Every boat measured the same way.
A consistent performance-archetype framework, applied to every boat in the ORC fleet.