Airfoil Self Noise
Airfoil Self Noise dataset with 1,503 records for regression.
Business Objective: Airfoil Self Noise
01Business Context
Curated tabular benchmark dataset from UCI.
02Analytical Objective
Predict target variable 'scaled-sound-pressure' using available features.
03Economic & Decision Impact
High accuracy models enable automated data-driven decision-making.
Evaluated under iid evaluation regime with cross-validation splits.
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 6 columns.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| F | scaled-sound-pressureScaled-Sound-Pressure | TARGET | NUM | — | Target variable for Airfoil Self Noise |
| A | frequencyFrequency | Feature | NUM | — | Feature attribute for Airfoil Self Noise |
| B | attack-angleAttack-Angle | Feature | CAT | — | Feature attribute for Airfoil Self Noise |
| C | chord-lengthChord-Length | Feature | NUM | — | Feature attribute for Airfoil Self Noise |
| D | free-stream-velocityFree-Stream-Velocity | Feature | NUM | — | Feature attribute for Airfoil Self Noise |
| E | suction-side-displacement-thicknessSuction-Side-Displacement-Thickness | Feature | NUM | — | Feature attribute for Airfoil Self Noise |
Interactive Data Table
Explore rows, feature values, and target labels for Airfoil Self Noise.
TabICLv2 WebGPU Benchmark Results
Complete performance metrics on persisted IID or non-IID evaluation splits, executed 100% locally in the browser sandbox.
| Evaluation Split | Train Rows | Test Rows | Split Duration?Wall-clock inference time taken for this evaluation split running 100% locally via WebGPU.Learn more → | R² Score?Coefficient of determination measuring variance explained by the model.Learn more → | MAE?Mean Absolute Error in original target units, robust to outliers.Learn more → | RMSE?Root Mean Squared Error, penalizing large residual deviations.Learn more → | MAPE?Mean Absolute Percentage Error relative to true target values.Learn more → | RMSLE?Root Mean Squared Logarithmic Error, measuring proportional error scales.Learn more → |
|---|---|---|---|---|---|---|---|---|
| R1 / F1 | 1,002 | 501 | 4.42s | 0.9702 | 0.76 | 1.22 | — | — |
| R1 / F2 | 1,002 | 501 | 4.08s | 0.9784 | 0.67 | 1 | — | — |
| R1 / F3 | 1,002 | 501 | 4.06s | 0.9777 | 0.7 | 1.02 | — | — |
| R2 / F1 | 1,002 | 501 | 4.05s | 0.9768 | 0.7 | 1.07 | — | — |
| R2 / F2 | 1,002 | 501 | 4.06s | 0.9666 | 0.74 | 1.22 | — | — |
| R2 / F3 | 1,002 | 501 | 4.05s | 0.9782 | 0.68 | 1.03 | — | — |
| R3 / F1 | 1,002 | 501 | 4.03s | 0.9806 | 0.63 | 0.96 | — | — |
| R3 / F2 | 1,002 | 501 | 4.06s | 0.9671 | 0.76 | 1.25 | — | — |
| R3 / F3 | 1,002 | 501 | 4.07s | 0.9733 | 0.74 | 1.12 | — | — |
| R4 / F1 | 1,002 | 501 | 4.02s | 0.9668 | 0.71 | 1.23 | — | — |
| R4 / F2 | 1,002 | 501 | 4.06s | 0.9785 | 0.69 | 1 | — | — |
| R4 / F3 | 1,002 | 501 | 4.01s | 0.9713 | 0.74 | 1.2 | — | — |
| R5 / F1 | 1,002 | 501 | 4.01s | 0.9753 | 0.68 | 1.07 | — | — |
| R5 / F2 | 1,002 | 501 | 4.02s | 0.9703 | 0.75 | 1.22 | — | — |
| R5 / F3 | 1,002 | 501 | 4.01s | 0.9646 | 0.75 | 1.28 | — | — |
| R6 / F1 | 1,002 | 501 | 4.04s | 0.9759 | 0.73 | 1.09 | — | — |
| R6 / F2 | 1,002 | 501 | 4.04s | 0.9636 | 0.77 | 1.3 | — | — |
| R6 / F3 | 1,002 | 501 | 4.00s | 0.9737 | 0.71 | 1.11 | — | — |
| R7 / F1 | 1,002 | 501 | 4.05s | 0.9778 | 0.6 | 1.01 | — | — |
| R7 / F2 | 1,002 | 501 | 4.04s | 0.9741 | 0.76 | 1.13 | — | — |
| R7 / F3 | 1,002 | 501 | 4.04s | 0.9714 | 0.74 | 1.15 | — | — |
| R8 / F1 | 1,002 | 501 | 4.03s | 0.9716 | 0.72 | 1.16 | — | — |
| R8 / F2 | 1,002 | 501 | 4.06s | 0.9703 | 0.69 | 1.15 | — | — |
| R8 / F3 | 1,002 | 501 | 4.07s | 0.9752 | 0.71 | 1.11 | — | — |
| R9 / F1 | 1,002 | 501 | 4.04s | 0.9755 | 0.68 | 1.08 | — | — |
| R9 / F2 | 1,002 | 501 | 4.05s | 0.9788 | 0.66 | 0.98 | — | — |
| R9 / F3 | 1,002 | 501 | 4.03s | 0.9754 | 0.71 | 1.11 | — | — |
| R10 / F1 | 1,002 | 501 | 4.06s | 0.9757 | 0.67 | 1.01 | — | — |
| R10 / F2 | 1,002 | 501 | 4.09s | 0.9776 | 0.66 | 1.05 | — | — |
| R10 / F3 | 1,002 | 501 | 4.12s | 0.9783 | 0.69 | 1.05 | — | — |
| Mean ± Std | — | — | 4.06s | 0.9737 ± 0.0045 | 0.7 | 1.1 | — | — |
Foundation Models vs Traditional ML Baselines
Side-by-side evaluation of our in-browser Carla engine (WebGPU), open-source tabular foundation models, and OpenML baselines.
| Rank | Algorithm / Model | Model Family | Runtime | R² Score?Coefficient of determination (R²) measuring proportion of variance explained.Google ML Guide & Details → | MAE?Mean Absolute Error measuring average prediction error magnitude.Learn more → | RMSE?Root Mean Squared Error penalizing large prediction errors.Learn more → | Reference / Repo |
|---|---|---|---|---|---|---|---|
| #1 | TabPFN v3 | Tabular Foundation Model | PyTorch/Python | 0.9778 | 0.7 | 1 | PriorLabs/tabpfn ↗ |
| #2 | Google TabFM v1.0 | Tabular Foundation Model | PyTorch/Python | 0.9740 | 0.7 | 1.1 | google-research/tabfm ↗ |
| #3 | Carla Engine (TabICLv2 WebGPU) | Tabular Foundation Model | Browser | 0.9737 | 0.7 | 1.1 | 100% In-Browser |
| #4 | nanotabicl Vanilla | Tabular Foundation Model | PyTorch/Python | 0.9733 | 0.7 | 1.1 | soda-inria/nanotabicl ↗ |
| #5 | Full TabICLv2 (PyTorch Reference) | Tabular Foundation Model | PyTorch/Python | 0.9733 | 0.7 | 1.1 | soda-inria/tabicl ↗ |
| #6 | Streaming nanotabicl | Tabular Foundation Model | PyTorch/Python | 0.9733 | 0.7 | 1.1 | soda-inria/nanotabicl ↗ |
| #7 | EXAONE Tabular | Tabular Foundation Model | PyTorch/Python | 0.9715 | 0.7 | 1.2 | LGAI-Research/EXAONE-Tabular ↗ |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 1,503 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| F | scaled-sound-pressureTARGET | NUM | 0 | 1,456 | [103.38, 140.987] μ=124.8 σ=6.9 | 125.045118.767120.233 |
| A | frequency | NUM | 0 | 21 | [200, 20000] μ=2886.4 σ=3152.6 | 40012502500 |
| B | attack-angle | CAT | 0 | 27 | — | 012.34 |
| C | chord-length | NUM | 0 | 6 | [0.0254, 0.3048] μ=0.1 σ=0.1 | 0.30480.10160.3048 |
| D | free-stream-velocity | NUM | 0 | 4 | [31.7, 71.3] μ=50.9 σ=15.6 | 31.731.739.6 |
| E | suction-side-displacement-thickness | NUM | 0 | 105 | [0.0004, 0.0584] μ=0.0 σ=0.0 | 0.00330.04190.0058 |
Frequently Asked Questions: Airfoil Self Noise
Common questions regarding the Airfoil Self Noise dataset, machine learning task formulations, and in-browser tabular inference.
What is the prediction task in Airfoil Self Noise?
The objective is to predict 'scaled-sound-pressure' using tabular foundation models like TabICL.
Test TabICLv2 on Airfoil Self Noise Yourself
Open the pre-loaded Google Sheet and let Carla configure the target and task for local, zero-cloud tabular machine learning.
Launch Carla
Click once to open the spreadsheet and Carla side panel together.
Review the Setup
Carla selects the dataset target and task from this page automatically.
Evaluate & Predict
Run predictions and compute metrics with zero server uploads.
Provenance & Attribution
@techreport{brooks1989airfoil, title={Airfoil self-noise and prediction}, author={Brooks, Thomas F and Pope, D Stuart and Marcolini, Michael A}, year={1989} }