NeuralHydrology

Predicts streamflow from rainfall using LSTM models

Field
Hydrology
Method
Deep learning
Data it takes
time-series
License
BSD-3-Clause

NeuralHydrology trains and runs LSTM rainfall-runoff models, which have matched or exceeded conceptual hydrological models on benchmark catchments. Models pretrained on CAMELS provide a starting point for gauged basins.

Runs on CPU. Where a catchment has insufficient history for fine-tuning, TimesFM forecasts without training.

Upstream project →

Catalog entry last checked 2026-08-17. All models →

Run NeuralHydrology on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab