Skip to main content
CARLA HQ
UCI Operations & Workforce Analytics use casesNACE M72RegressionTarget: scaled-sound-pressure

Airfoil Self Noise

Airfoil Self Noise dataset with 1,503 records for regression.

✨ Try in CarlaInstall Chrome Extension ↗100% In-Browser WebGPU • Zero Cloud Upload
1,503Records (Rows)
5Predictive Features
5 / 1Numeric / Categorical
0.0%Missing Value Ratio
1.12RMSE
4.06sWebGPU Mean Split
BUSINESS CONTEXT & OBJECTIVEPredictive Machine Learning Benchmark (M72)

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.

ML Benchmark Narrative

Evaluated under iid evaluation regime with cross-validation splits.

Source Origin:UCI
Creator:brooks1989airfoil
License:CC BY 4.0
FEATURE SPECIFICATION & DATA DICTIONARY

Target & Feature Column Definitions

Exhaustive business definitions, measurement units, roles, and target variables across all 6 columns.

ColVariable / Feature NameRoleTypeUnit / ScaleDescription & Business Meaning
Fscaled-sound-pressureScaled-Sound-PressureTARGETNUM
Target variable for Airfoil Self Noise
AfrequencyFrequencyFeatureNUM
Feature attribute for Airfoil Self Noise
Battack-angleAttack-AngleFeatureCAT
Feature attribute for Airfoil Self Noise
Cchord-lengthChord-LengthFeatureNUM
Feature attribute for Airfoil Self Noise
Dfree-stream-velocityFree-Stream-VelocityFeatureNUM
Feature attribute for Airfoil Self Noise
Esuction-side-displacement-thicknessSuction-Side-Displacement-ThicknessFeatureNUM
Feature attribute for Airfoil Self Noise
DATASET PREVIEW

Interactive Data Table

Explore rows, feature values, and target labels for Airfoil Self Noise.

Loading dataset...
LOCAL EXECUTION TELEMETRY

TabICLv2 WebGPU Benchmark Results

Complete performance metrics on persisted IID or non-IID evaluation splits, executed 100% locally in the browser sandbox.

Mean Split Latency?Mean wall-clock execution time per persisted evaluation split running 100% locally via WebGPU inside Chrome.Explore Latency Guide →
4.06s30 splits • 8 ensembles/split
Total Evaluation Runtime?Total wall-clock duration across all selected splits, including in-context encoding, WebGPU shader execution, and result aggregation.Explore Split Protocol →
121.79sIncludes warmup & sync
Evaluation Protocol?Precomputed row indices ensure the browser and Python runners evaluate identical out-of-sample observations without leakage.Explore Split Protocol →
10×3 SplitsRepeated IID • 30 total
TabICLv2 Score?Primary task performance score (RMSE) achieved by TabICLv2 across out-of-sample evaluation splits.Explore Metric Formula →
1.12RMSE
Evaluation SplitTrain RowsTest 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 / F11,0025014.42s0.97020.761.22
R1 / F21,0025014.08s0.97840.671
R1 / F31,0025014.06s0.97770.71.02
R2 / F11,0025014.05s0.97680.71.07
R2 / F21,0025014.06s0.96660.741.22
R2 / F31,0025014.05s0.97820.681.03
R3 / F11,0025014.03s0.98060.630.96
R3 / F21,0025014.06s0.96710.761.25
R3 / F31,0025014.07s0.97330.741.12
R4 / F11,0025014.02s0.96680.711.23
R4 / F21,0025014.06s0.97850.691
R4 / F31,0025014.01s0.97130.741.2
R5 / F11,0025014.01s0.97530.681.07
R5 / F21,0025014.02s0.97030.751.22
R5 / F31,0025014.01s0.96460.751.28
R6 / F11,0025014.04s0.97590.731.09
R6 / F21,0025014.04s0.96360.771.3
R6 / F31,0025014.00s0.97370.711.11
R7 / F11,0025014.05s0.97780.61.01
R7 / F21,0025014.04s0.97410.761.13
R7 / F31,0025014.04s0.97140.741.15
R8 / F11,0025014.03s0.97160.721.16
R8 / F21,0025014.06s0.97030.691.15
R8 / F31,0025014.07s0.97520.711.11
R9 / F11,0025014.04s0.97550.681.08
R9 / F21,0025014.05s0.97880.660.98
R9 / F31,0025014.03s0.97540.711.11
R10 / F11,0025014.06s0.97570.671.01
R10 / F21,0025014.09s0.97760.661.05
R10 / F31,0025014.12s0.97830.691.05
Mean ± Std4.06s0.9737 ± 0.00450.71.1
UNIFIED BENCHMARK LEADERBOARD

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.

RankAlgorithm / ModelModel FamilyRuntime
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
#1TabPFN v3Tabular Foundation ModelPyTorch/Python0.97780.71PriorLabs/tabpfn ↗
#2Google TabFM v1.0Tabular Foundation ModelPyTorch/Python0.97400.71.1google-research/tabfm ↗
#3Carla Engine (TabICLv2 WebGPU)Tabular Foundation ModelBrowser0.97370.71.1100% In-Browser
#4nanotabicl VanillaTabular Foundation ModelPyTorch/Python0.97330.71.1soda-inria/nanotabicl ↗
#5Full TabICLv2 (PyTorch Reference)Tabular Foundation ModelPyTorch/Python0.97330.71.1soda-inria/tabicl ↗
#6Streaming nanotabiclTabular Foundation ModelPyTorch/Python0.97330.71.1soda-inria/nanotabicl ↗
#7EXAONE TabularTabular Foundation ModelPyTorch/Python0.97150.71.2LGAI-Research/EXAONE-Tabular ↗
STATISTICAL DISTRIBUTIONS

Variable Schema & Summary Distributions

Observed numerical ranges, category cardinalities, missing rates, and sample values across 1,503 rows.

ColVariable NameTypeMissingDistinctSummary Stats / DistributionSample Values
Fscaled-sound-pressureTARGETNUM01,456[103.38, 140.987] μ=124.8 σ=6.9125.045118.767120.233
AfrequencyNUM021[200, 20000] μ=2886.4 σ=3152.640012502500
Battack-angleCAT027012.34
Cchord-lengthNUM06[0.0254, 0.3048] μ=0.1 σ=0.10.30480.10160.3048
Dfree-stream-velocityNUM04[31.7, 71.3] μ=50.9 σ=15.631.731.739.6
Esuction-side-displacement-thicknessNUM0105[0.0004, 0.0584] μ=0.0 σ=0.00.00330.04190.0058
FREQUENTLY ASKED QUESTIONS

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.

LIVE EVALUATION IN GOOGLE SHEETS

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.

Step 1

Launch Carla

Click once to open the spreadsheet and Carla side panel together.

Step 2

Review the Setup

Carla selects the dataset target and task from this page automatically.

Step 3

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} }

License: CC BY 4.0Data Source: UCIOriginal Source: https://doi.org/10.24432/C5VW2C