Hidden

Full-Waveform Inversion (FWI) — Hidden Tier

(5 scenes)

Fully blind server-side evaluation — no data download.

What you get

No data downloadable. Algorithm runs server-side on hidden measurements.

How to use

Package algorithm as Docker container / Python script. Submit via link.

What to submit

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
starting_velocity_model_error -2.1 – 6.9 -
source_wavelet_error -1.4 – 4.6 -
anelastic_attenuation_(q) -70.0 – 230.0 -
source_location_error -14.0 – 46.0 m

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 TV-Reg FWI + gradient 0.600 23.8 0.761 0.79 ✓ Certified Esser et al., Geophysics 2018
2 InversionNet + gradient 0.597 23.48 0.75 0.81 ✓ Certified Wu & Lin, JGR 2019
3 VelocityGAN + gradient 0.592 23.78 0.761 0.75 ✓ Certified Zhang & Lin, JGR 2020
4 L-BFGS FWI + gradient 0.448 18.01 0.5 0.84 ✓ Certified Virieux & Operto, Geophysics 2009

Dataset

Scenes: 5

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to Full-Waveform Inversion (FWI)