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

Download

Final revised paper (published on 19 Apr 2021)
Preprint (discussion started on 17 Nov 2020)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Comments to "Rainfall–Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network"', Jens Kiesel, 14 Dec 2020
- AC2: 'Reply on RC1', Martin Gauch, 08 Feb 2021
RC2: 'An excellent research article exploiting the flexibility of data-driven models for rainfall-runoff modelling', Thomas Lees, 03 Jan 2021
- AC1: 'Reply on RC2', Martin Gauch, 08 Feb 2021

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

ED: Publish subject to revisions (further review by editor and referees) (08 Feb 2021) by Fabrizio Fenicia

AR by Martin Gauch on behalf of the Authors (15 Feb 2021) Author's response Author's tracked changes Manuscript

ED: Referee Nomination & Report Request started (02 Mar 2021) by Fabrizio Fenicia

RR by Jens Kiesel (05 Mar 2021)

ED: Publish subject to technical corrections (17 Mar 2021) by Fabrizio Fenicia

AR by Martin Gauch on behalf of the Authors (18 Mar 2021) Author's response Manuscript

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.