OuyangWenyu/torchhydro
TorchHydro: datasets, and models for watershed hydrological modeling
This tool helps hydrologists and water resource managers create accurate predictions for water flow in watersheds. It takes historical weather data, streamflow measurements, and watershed characteristics as input, and outputs trained deep learning models that can forecast future streamflow. It is designed for researchers and practitioners in hydrology who want to apply advanced machine learning techniques to real-world water modeling challenges.
Available on PyPI.
Use this if you need to build, train, and evaluate deep learning models for hydrological forecasting, especially using datasets like CAMELS.
Not ideal if you are looking for a pre-built, ready-to-use forecasting application rather than a toolkit for model development and research.
Stars
22
Forks
26
Language
Python
License
—
Category
Last pushed
Dec 30, 2025
Commits (30d)
0
Dependencies
23
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OuyangWenyu/torchhydro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
mhpi/hydrodl2
Repository for MHPI differentiable hydrological models.
confidence-duku/bakaano-hydro
A distributed hydrology-guided neural network model for streamflow prediction
WaterFutures/water-futures-battle
Part of the Battle of Water Networks competition series | WDSA/CCWI 2026, May 18-21, Paphos,...
IBM/Environmental-Intelligence-Suite
IBM Environmental Intelligence Suite
KageRyo/MPR_Model
💧MPR_Model: AI-powered Water Quality Analysis's Model for WaterMirror