Drag, lift, and shedding scored identically for model and solver.

Published 4 Aug 2026, updated 14 Nov 2026

Low global velocity error does not guarantee accurate surface forces. We run the exact same control-volume and traction post-processing on predicted and simulated fields to verify drag, lift, surface Cp, and vortex-shedding frequency.

Evaluated 9 Jul 2026

Derived aerodynamic quantities & shedding lock.

Across three held-out bluff and aerodynamic geometries from Re = 104 to 355, derived forces match the reference simulation within 0.5–1.6% (force RelL2 0.001–0.016) and lock onto the reference vortex-shedding frequency at St = 0.128.

Load accuracy band 0.5–1.6% Across horizon ladder
Force RelL2 0.001–0.016 Held-out Re 104–355
Shedding Strouhal 0.128 Matches 0.128 solver
Mid-hump load RelL2 0.005 vs 0.052 wake vorticity
FIG 1.0: Force & field decoupling

Where field error lives, and why surface loads stay tight.

Even where downstream wake vorticity experiences a mid-horizon phase hump (0.052 RelL2), near-body pressure recovery holds integrated force error at 0.005.

Plate 1.0: Drag, lift, and spatial error localization (Re 104–355) Measured Identical post-processing on solver & learned map
Aero-quantity evaluation: drag and lift coefficients for solver and model, and field versus load error
Three held-out geometries (Re 104 to 355): Integrated drag and lift trajectories track the numerical reference to 0.5–1.6%. The transient mid-horizon hump resides in downstream vortex advection phase (vorticity RelL2 0.052), leaving near-wall force integration at 0.005.
FIG 1.1: Shedding periodicity

Strouhal lock: St 0.128 = 0.128.

Time-averaged drag can look acceptable even when an operator damps out Karman vortex shedding. Scrub the phase-alignment scope to see how unlocked phase or amplitude error compares against the measured St = 0.128 frequency match.

Solver CL(t) Learned CL(t) f* = St 0.128
Phase locked (Δφ 0.00 rad)
Illustrative Schematic waveform of measured St 0.128 = 0.128 frequency match
Schematic waveform of measured frequency

The Strouhal match (St = 0.128 on both reference solver and learned flow map) is a measured result from the unsteady evaluation above; the interactive oscilloscope renders a clean schematic C_L(t) sinusoid so you can inspect phase-offset sensitivity directly.

FIG 2.0: Quantitative ledger

Published load & frequency metrics.

All four numbers below come from held-out geometries with zero separate force-regression head: forces are integrated directly from the predicted fluid fields.

0.5–1.6%
Reported load error band between model-derived and solver-derived integrated forces across the horizon ladder.
0.001–0.016
Force Relative L2 range across three held-out geometries spanning Re = 104 to 355.
0.128St
Dimensionless vortex-shedding frequency (f·D/U∞), matching the reference simulation’s 0.128.
0.005vs 0.052
Force RelL2 at the mid-horizon field hump, showing 10× lower sensitivity in surface loads than in far-wake vorticity phase (0.052).
FIG 3.0: 3D Studio load recovery

Inspect 24-tap surface Cp(s) and 6-DOF tractions in 3D.

In Reyn Studio’s 3D CAD workflow, pressure is recovered from the predicted velocity field and integrated via diffuse_interface_traction.v1. Switch across all four cleared 3D reference bodies and scrub individual perimeter taps.

24-tap centerline surface Cp(s) and integrated fluid loads (diffuse_interface_traction.v1)
Recorded in Reyn Studio Studio 0.4.1, Re 150, velocity-recovered Cp
Centerline section (z = 0), 24 perimeter taps Click or scrub tap 1–24
Surface Cp(s/S) around closed section Peak 0.397
0.0 0.2 0.4 0.6 s/S = 0 (nose) 0.50 (base) 1.00
Arc s/S0.021
Coord (x, y)(−0.80, +0.08)
Normal n̂(−1.00, +0.06)
Surface Cp+0.321
Force decomposition 85% pressure, 15% viscous
Cx (drag)+0.1891
Cy+0.0239
Cz+0.0070
CMx−0.0002
CMy (pitch)−0.0017
CMz (yaw)−0.0031
Fluid tractions vs. structural stress

Coefficients in the 3D Studio inspector above are model-derived fluid diagnostics at Re = 150 on a 32³ grid, rather than high-Reynolds wind-tunnel measurements or internal solid-mechanics stress. Moments are referenced to the diffuse-surface area centroid for relative candidate ranking and downstream FEA load mapping.

Scoring parity

Why we forbid separate scalar Cd/Cl shortcuts.

Predicting a single scalar drag number from a point cloud is easy to overfit and impossible for an aero lead to audit physically.

Field-first derivation
Every force, moment, and Cp curve is computed from the predicted spatially resolved flow field rather than an ungrounded scalar MLP head.
Identical operator
The exact same numerical integration routine processes both the ground-truth solver state and the neural flow-map state, eliminating post-processing bias.
Inspection parity
If a drag delta looks surprising between two CAD variants, engineers can immediately slice the centerline Cp(s) taps and wake deficit plane to verify the physical cause.
Operating boundaries

What these numbers do and do not claim.

Every held-out score on this site is paired with the grid, regime, and failure gate that bound it in production.

Qualification

Verification, not certification

Relative L2, force RelL2, and Strouhal checks measure discrepancy against reference solvers on held-out test sets. They do not certify Reyn Studio for flight, road, marine, or safety-critical sign-off.

Grid resolution

Declared 32³ voxel grid

The shipping 3D research operator resolves 32,768 cells. Imported CAD thinner than one cell along any axis is refused before inference rather than extrapolated across empty solid voxels.

Flow regime

Tested Reynolds & horizon scope

Published scores cover laminar/transitional bluff-body wake regimes (Re = 100–355 in 2D; Re = 150 to 128 solver steps in 3D, RelL2 0.052). High-Reynolds RANS/LES boundary layers are outside current bundle scope.

Derived loads

Derived pressure & fluid tractions

Surface Cp is recovered from the predicted velocity field, and diffuse-interface tractions represent fluid loads for relative ranking or downstream FEA mapping, not internal structural stress.

Evaluate a geometry.

Studio packages are public to download; credentials are issued after review for external-flow candidate screening.