Observed arrival · 2026-10-21
HydrologyMIP: shared benchmarks for hydrological models
A research benchmarking project that compares hydrological models using shared catchments, evaluation protocols, leaderboards, and prediction archives.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Hydrology researchers comparing rainfall–runoff models
- Worth noticing
- The CAMELS-US specification sets 531 basins, a 12-fold PUB split, and an 18-fold HUC-02 PUR split.
Field notes
For CAMELS-US, the listed screening retains 531 basins under 2,000 km² with no more than 10% area error. The training window is 1999-10-01 to 2008-09-30, while evaluation uses 1989-10-01 to 1999-09-30; separate 12-fold PUB and 18-region PUR splits define out-of-sample tests. The page also lists four CAMELS-US forcing categories and says model entries require archived predictions.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue