Rainfall–runoff prediction at multiple timescales with a single Long Short-Term Memory network

Gauch, Martin; Kratzert, Frederik; Klotz, Daniel; Nearing, Grey; Lin, Jimmy; Hochreiter, Sepp

doi:https://doi.org/10.5194/hess-25-2045-2021

Articles | Volume 25, issue 4

https://doi.org/10.5194/hess-25-2045-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-25-2045-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 25, issue 4

Research article

|

19 Apr 2021

Research article |

| 19 Apr 2021

Rainfall–runoff prediction at multiple timescales with a single Long Short-Term Memory network

Martin Gauch, Frederik Kratzert, Daniel Klotz, Grey Nearing, Jimmy Lin, and Sepp Hochreiter

Data sets

Data for "Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network" Martin Gauch, Frederik Kratzert, Daniel Klotz, Grey Nearing, Jimmy Lin, and Sepp Hochreiter https://doi.org/10.5281/zenodo.4071885

Data for "Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network" Martin Gauch, Frederik Kratzert, Daniel Klotz, Grey Nearing, Jimmy Lin, and Sepp Hochreiter https://doi.org/10.5281/zenodo.4072700

Catchment attributes for large-sample studies N. Addor, A. Newman, M. Mizukami, and M. P. Clark https://doi.org/10.5065/D6G73C3Q

CAMELS Extended Maurer Forcing Data Frederik Kratzert https://doi.org/10.4211/hs.17c896843cf940339c3c3496d0c1c077

Model code and software

Code for "Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network" Martin Gauch https://doi.org/10.5281/zenodo.4687991

NeuralHydrology Python Library Frederik Kratzert, Martin Gauch, and Daniel Klotz https://doi.org/10.5281/zenodo.4688003

Short summary

We present multi-timescale Short-Term Memory (MTS-LSTM), a machine learning approach that predicts discharge at multiple timescales within one model. MTS-LSTM is significantly more accurate than the US National Water Model and computationally more efficient than an individual LSTM model per timescale. Further, MTS-LSTM can process different input variables at different timescales, which is important as the lead time of meteorological forecasts often depends on their temporal resolution.