A Data Fusion Framework for Grounding Aerospace Surrogate Model via Experimental Wind-Tunnel Observations

Nitin Nagesh Kulkarni; Dheeraj Vemula; Yin Yu; Peter Lyu; Juan J. Alonso

cs.LGSep 2, 2026

A Data Fusion Framework for Grounding Aerospace Surrogate Model via Experimental Wind-Tunnel Observations

Authors: Nitin Nagesh Kulkarni, Dheeraj Vemula, Yin Yu, Peter Lyu, Juan J. Alonso

Organizations: Luminary AI 101 S Ellsworth Ave, San Mateo, CA, USA

Abstract

Aerodynamic surrogate models trained on high-fidelity CFD data reproduce numerical predictions of both scalar outputs and entire fields accurately, yet their predictive fidelity is limited by systematic discrepancies between CFD and experimental observations. We present an experimentally grounded correction framework that adapts a CFD-trained deep learning surrogate using wind-tunnel PSP measurements. A Geotransolver surrogate trained on 2,300 high-fidelity CFD simulations of the NASA CRM wing-body configuration, spanning geometric variation, Mach 0.70-0.85, and angles of attack 0 to 4 degrees, reproduces the CFD integrated aerodynamic forces and pitching moment to R2 > 0.99 but does not match the experimental data. To incorporate experimental information without retraining the surrogate, a correction network is trained on spatially registered PSP measurements at two freestream Mach numbers (0.70 and 0.85) across the same angle-of-attack range, learning the discrepancy between the surrogate-predicted and experimentally measured surface-pressure distributions. At Mach 0.85 the correction substantially improves agreement with PSP, particularly at the wing suction peak, shock location, and subsequent pressure recovery, reducing both the magnitude of the prediction error and the fraction of wetted surface on which it exceeds 0.05 in Cp, and it does so from a limited experimental dataset without modifying the pretrained surrogate parameters. On held-out angles of attack the grounded surrogate agrees with measurement to within 2.3-2.7% of the measured Cp range, and outperforms direct interpolation between the measured conditions at every state tested. Experimental measurements can therefore ground a large-scale simulation-trained surrogate by learning systematic CFD-to-experiment discrepancies while preserving its generalization capability and computational efficiency.

Figures & tables

Panel of Figure 1 — Figure 1: (a) Overview of the proposed simulation-to-experiment grounding framework. (b) Baseline architecture: training the surrogate on high-fidelity CFD datasets. (c) Correction framework: fine-tuning the surrogate using experimental data to learn the CFD-to-experiment discrepancy.

Figure 2: Lift, drag and pitching moments: baseline geotransolver surrogate model performance across the Mach 0.70 to 0.85 and AoA 0 ∘ to 4 ∘ flight envelope.

Panel of Figure 3 — Figure 3: (a) Spanwise $C_{p}$ distributions at $M=0.85$ comparing CFD, PSP, and corrected predictions at AoA 1.5 ∘ (a–c) and 3.0 ∘ (d–f) from near-root to near-tip. (b) Surface $C_{p}$ fields from PSP, uncorrected, and corrected predictions.

$M$	AoA	$R^{2}$	MAE	RMSE	Norm. err. (%)	$C_{p}$ range
0.70	1.5 ∘	0.940	0.059	0.090	2.4	2.44
0.70	3.0 ∘	0.966	0.065	0.100	2.3	2.82
0.85	1.5 ∘	0.922	0.069	0.110	2.5	2.75
0.85	3.0 ∘	0.952	0.070	0.110	2.7	2.64

Table 1: Per-condition agreement between the grounded surrogate and PSP at held-out states. Normalized error is MAE divided by the measured

C_{p}

range.

Condition	raw	registered	surrogate	registration	correction
	Interpolation baseline		Grounded	$\Delta R^{2}$ from
$M=0.70$ , AoA $=$ 1.5 ∘	0.743	0.849	0.940	$+0.106$	$+0.091$
$M=0.70$ , AoA $=$ 3.0 ∘	0.710	0.874	0.966	$+0.164$	$+0.092$
$M=0.85$ , AoA $=$ 1.5 ∘	0.722	0.828	0.922	$+0.106$	$+0.094$
$M=0.85$ , AoA $=$ 3.0 ∘	0.655	0.756	0.952	$+0.101$	$+0.196$

Table 2: Surface

C_{p}

agreement with PSP at held-out conditions. Interpolation uses raw, registered PSP fields, while the grounded surrogate combines the frozen backbone with the correction head.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Variable	Meaning	Range
$AR$	Aspect ratio	7.5 – 11
$\Lambda_{c/4}$	Quarter-chord sweep ( ∘ )	25 – 37.5
$f_{c_{r}}$	Root-chord extension factor	1.0 – 1.4
$D_{f}$	Fuselage diameter (m)	6.096 – 6.553
$\tau_{r}$	Root twist ( ∘ )	3 – 9
$\Delta\tau_{k}$	Kink twist increment ( ∘ )	$-7$ to $-3$

Appendix

Table 3: Design of experiments for the SHIFT-Wing dataset. The seven geometry variables are sampled by Latin hypercube; angle of attack is swept and sideslip is fixed.

Figure 4: Coordinate registration pipeline. The delivered PSP field is indexed by structured grid position, so chordwise and spanwise coordinates are first reconstructed from the grid indices (Stage 1); the resulting measurement cloud is transferred onto the CFD surface nodes by inverse-distance weighted interpolation (Stage 2); and a Gaussian process is fitted over the surface to suppress measurement noise and fill nodes left without a valid paint return (Stage 3). The output is a registered $C_{p}^{\mathrm{exp}}$ field carrying one value per CFD mesh cell, which is the target used for fitting and evaluating the correction head. Cells with no valid PSP return are masked and excluded from both.

Figure 5: Surface $C_{p}$ parity plots: predicted versus experimental ground truth $C_{p}$ across Mach 0.70 and 0.85 at AoA $=$ 1.5 ∘ and 3.0 ∘ .

Figure 6: Spanwise $C_{p}$ distribution: comparison of baseline CFD, experimental PSP measurements, and calibrated surrogate model predictions at Mach 0.70 across spanwise sections ( $\eta=0.15$ near root, $\eta=0.50$ mid-span, and $\eta=0.85$ near tip) for AoA $=$ 1.5 ∘ (a–c) and AoA $=$ 3.0 ∘ (d–f).

Panel of Figure 7 — Figure 7: Full-surface $C_{p}$ contours and error maps at Mach 0.70: comparison of experimental ground truth, Geotransolver prediction, and spatial error field. (a) AoA $=$ 1.5 ∘ ( $R^{2}=0.940$ , MAE $=0.059$ ). (b) AoA $=$ 3.0 ∘ ( $R^{2}=0.966$ , MAE $=0.065$ ).

Neural Surrogate Modeling

Neural surrogate modeling uses learned models to approximate costly simulations, enabling faster prediction, design, control, and inference.

See all 410 papers

Neural Field Ensembles for Aerodynamic Surface Prediction: Winning Solution to the ONERA CRM Wall Distribution 2025 Challenge
Sep 15, 2026Lionel Salesses, Caroline Sainvitu, Tariq BenamaraNeural Surrogate Modeling Implicit Neural Representations
Cenaero, Gosselies, Belgium
Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction
Apr 13, 2026Víctor Francés-Belda, Carlos Sanmiguel Vila, Rodrigo CastellanosConditional Diffusion Models Computational Fluid Dynamics
Theoretical and Computational Aerodynamics Group Flight Physics Department. Subdirectorate General for Aeronautical Systems Spanish National Institute for Aerospace Technology (INTA) · Department of Aerospace Engineering Universidad Carlos III de Madrid Madrid, Spain · Aerial Platforms Department Subdirectorate General for Aeronautical Systems Spanish National Institute for Aerospace Technology (INTA)
Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD
Apr 20, 2026Nicholas Thumiger, Andrea Bartezzaghi, Mattia Rigotti +5PDE Surrogate Modeling Graph Neural Operators
IBM Research · Dallara Automobili

Sep 15, 2026J/K move · Enter open · S save

Neural Field Ensembles for Aerodynamic Surface Prediction: Winning Solution to the ONERA CRM Wall Distribution 2025 Challenge

Lionel Salesses, Caroline Sainvitu, Tariq Benamara

Cenaero, Gosselies, Belgium

Neural Surrogate Modeling Implicit Neural Representations Computational Fluid Dynamics

Open paper AskPDF arXiv

Machine-learning surrogate models offer a promising alternative to high-fidelity Computational Fluid Dynamics (CFD) simulations for aerodynamic analysis and design. However, constructing accurate surrogates for realistic aircraft configurations remain challenging due to complex geometries, multiple flow regimes, and limited training data. This work presents the methodology that achieved first place in the ONERA CRM Wall Distribution Regression Challenge, which focuses on predicting pressure and skin-friction coefficient distributions over the NASA Common Research Model wing-body-pylon-nacelle configuration under different operating conditions. The proposed approach formulates the problem as a conditional neural field mapping spatial coordinates, surface normals, and operating conditions to aerodynamic wall quantities. Fourier feature encoding, a relative squared error objective aligned with the challenge metric, ensemble learning, and

k

-fold cross-validation are progressively introduced to improve prediction accuracy and exploit the limited training data. Beyond presenting the final methodology, the paper documents the successive model design choices that led to the winning solution through a comprehensive ablation study and discusses several alternative approaches that were investigated but ultimately discarded. On the hidden competition test set, the proposed methodology achieves an overall score of 8.81, outperforming the strongest organizer-provided baseline, which achieved a score of 8.64, while requiring approximately three orders of magnitude fewer trainable parameters. These results illustrate that carefully designed coordinate-based neural fields constitute an efficient and robust framework for aerodynamic surrogate modeling on complex geometries under limited-data conditions.

Abstract

Neural Surrogate Modeling

Explore similar work

Neural Field Ensembles for Aerodynamic Surface Prediction: Winning Solution to the ONERA CRM Wall Distribution 2025 Challenge

Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction

Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD