Journal cover Journal topic
Hydrology and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 4.256 IF 4.256
  • IF 5-year value: 4.819 IF 5-year 4.819
  • CiteScore value: 4.10 CiteScore 4.10
  • SNIP value: 1.412 SNIP 1.412
  • SJR value: 2.023 SJR 2.023
  • IPP value: 3.97 IPP 3.97
  • h5-index value: 58 h5-index 58
  • Scimago H index value: 99 Scimago H index 99
Volume 22, issue 11
Hydrol. Earth Syst. Sci., 22, 6005-6022, 2018
https://doi.org/10.5194/hess-22-6005-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Hydrol. Earth Syst. Sci., 22, 6005-6022, 2018
https://doi.org/10.5194/hess-22-6005-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 22 Nov 2018

Research article | 22 Nov 2018

Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks

Frederik Kratzert1,*, Daniel Klotz1, Claire Brenner1, Karsten Schulz1, and Mathew Herrnegger1 Frederik Kratzert et al.
  • 1Institute of Water Management, Hydrology and Hydraulic Engineering, University of Natural Resources and Life Sciences, Vienna, 1190, Austria
  • * Invited contribution by Frederik Kratzert, recipient of the EGU Hydrological Sciences Outstanding Student Poster and PICO Award 2016.

Abstract. Rainfall–runoff modelling is one of the key challenges in the field of hydrology. Various approaches exist, ranging from physically based over conceptual to fully data-driven models. In this paper, we propose a novel data-driven approach, using the Long Short-Term Memory (LSTM) network, a special type of recurrent neural network. The advantage of the LSTM is its ability to learn long-term dependencies between the provided input and output of the network, which are essential for modelling storage effects in e.g. catchments with snow influence. We use 241 catchments of the freely available CAMELS data set to test our approach and also compare the results to the well-known Sacramento Soil Moisture Accounting Model (SAC-SMA) coupled with the Snow-17 snow routine. We also show the potential of the LSTM as a regional hydrological model in which one model predicts the discharge for a variety of catchments. In our last experiment, we show the possibility to transfer process understanding, learned at regional scale, to individual catchments and thereby increasing model performance when compared to a LSTM trained only on the data of single catchments. Using this approach, we were able to achieve better model performance as the SAC-SMA+Snow-17, which underlines the potential of the LSTM for hydrological modelling applications.

Publications Copernicus
Download
Short summary
In this paper, we propose a novel data-driven approach for rainfall–runoff modelling, using the long short-term memory (LSTM) network, a special type of recurrent neural network. We show in three different experiments that this network is able to learn to predict the discharge purely from meteorological input parameters (such as precipitation or temperature) as accurately as (or better than) the well-established Sacramento Soil Moisture Accounting model, coupled with the Snow-17 snow model.
In this paper, we propose a novel data-driven approach for rainfall–runoff modelling, using...
Citation
Share