Hidden
Weather / Doppler Radar — Hidden Tier
(3 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 |
|---|---|---|
| calibration_bias | -0.14 – 0.46 | dBZ |
| beam_elevation_error | -0.028 – 0.092 | deg |
| attenuation_correction | 0.986 – 1.046 | - |
| ground_clutter_leakage | -0.007 – 0.023 | - |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | Earthformer + gradient | 0.661 | 26.67 | 0.85 | 0.77 | ✓ Certified | Gao et al., NeurIPS 2022 |
| 2 | CLEAN-AP + gradient | 0.578 | 22.22 | 0.699 | 0.88 | ✓ Certified | Torres & Zrnic, IEEE TGRS 1999 |
| 3 | RainNet + gradient | 0.493 | 19.22 | 0.561 | 0.88 | ✓ Certified | Ayzel et al., GMD 2020 |
| 4 | Pulse-Pair Doppler + gradient | 0.484 | 19.08 | 0.554 | 0.86 | ✓ Certified | Zrnic, IEEE TAES 1977 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%