StormHub
Dewberry's open tool for building STAC catalogs of storms and gauge data — inputs for stochastic storm transposition.
The open global large-sample hydrology dataset — thousands of catchments with forcing, attributes and streamflow.
Caravan, initiated by Frederik Kratzert and collaborators, standardised what CAMELS started: a single open dataset of catchment attributes, meteorological forcing (ERA5-Land derived) and observed streamflow across thousands of basins worldwide, in one consistent format — plus the open pipeline for the community to extend it, which regional groups have done enthusiastically.
If you train or benchmark hydrological models — machine learning or conceptual — Caravan is the closest thing the field has to a common benchmark substrate. It pairs naturally with NeuralHydrology, and its community extensions keep widening coverage beyond the original countries.
Ranked by the topics, categories and workflow stages they share with Caravan.
Dewberry's open tool for building STAC catalogs of storms and gauge data — inputs for stochastic storm transposition.
An open-source take on Google Flood Hub — per-gauge neural network streamflow forecasting you can self-host.
A Python software stack for US hydrology data: NHD+ networks, gauges, DEMs, soils and climate via one API family.
Deep-learning rainfall-runoff modelling — the LSTM framework behind much of ML hydrology research.
Browser-based hydrology and hydraulics calculators for practising engineers — no install, report-ready output.
ECMWF's hourly global reanalysis — the default gap-free climate forcing record for ungauged catchments worldwide.