Preprints
https://doi.org/10.5194/hess-2023-124
https://doi.org/10.5194/hess-2023-124
30 May 2023
 | 30 May 2023
Status: a revised version of this preprint was accepted for the journal HESS.

Deep learning for monthly rainfall-runoff modelling: a comparison with classical rainfall-runoff modelling across Australia

Stephanie R. Clark, Julien Lerat, Jean-Michel Perraud, and Peter Fitch

Abstract. A deep learning model designed for time series predictions, the long short-term memory (LSTM) architecture is regularly producing reliable results in local and regional rainfall-runoff applications around the world. Recent large-sample-hydrology studies in North America and Europe have shown the LSTM to successfully match conceptual model performance at a daily timestep over hundreds of catchments. Here we investigate how these models perform in producing monthly runoff predictions in the relatively dry and variable conditions of the Australian continent. The monthly timestep matches historic data availability and is also important for future water resources planning, however it provides significantly smaller training data sets than daily time series. In this study, a continental-scale comparison of monthly deep learning (LSTM) predictions to conceptual rainfall-runoff model (WAPABA) predictions is performed on almost 500 catchments across Australia with performance results aggregated over a variety of catchment sizes, flow conditions, and hydrological record lengths. The study period covers a wet phase followed by a prolonged drought, introducing challenges for making predictions outside of known conditions - challenges that will intensify as climate change progresses. The results show that LSTMs matched or exceeded WAPABA prediction performance for more than two-thirds of the study catchments; the largest performance gains of LSTM versus WAPABA occurred in large catchments; the LSTM models struggled less to generalise than the WAPABA models (eg. making predictions under new conditions); and catchments with few training observations due to the monthly timestep did not demonstrate a clear benefit with either WAPABA or LSTM.

Stephanie R. Clark, Julien Lerat, Jean-Michel Perraud, and Peter Fitch

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2023-124', Martin Gauch, 03 Jul 2023
    • AC1: 'Reply on RC1', Stephanie Clark, 21 Aug 2023
      • AC3: 'Reply on AC1', Stephanie Clark, 21 Aug 2023
  • RC2: 'Comment on hess-2023-124', Umut Okkan, 12 Aug 2023
    • AC2: 'Reply on RC2', Stephanie Clark, 21 Aug 2023

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2023-124', Martin Gauch, 03 Jul 2023
    • AC1: 'Reply on RC1', Stephanie Clark, 21 Aug 2023
      • AC3: 'Reply on AC1', Stephanie Clark, 21 Aug 2023
  • RC2: 'Comment on hess-2023-124', Umut Okkan, 12 Aug 2023
    • AC2: 'Reply on RC2', Stephanie Clark, 21 Aug 2023
Stephanie R. Clark, Julien Lerat, Jean-Michel Perraud, and Peter Fitch
Stephanie R. Clark, Julien Lerat, Jean-Michel Perraud, and Peter Fitch

Viewed

Total article views: 797 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
599 176 22 797 12 9
  • HTML: 599
  • PDF: 176
  • XML: 22
  • Total: 797
  • BibTeX: 12
  • EndNote: 9
Views and downloads (calculated since 30 May 2023)
Cumulative views and downloads (calculated since 30 May 2023)

Viewed (geographical distribution)

Total article views: 755 (including HTML, PDF, and XML) Thereof 755 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 08 Feb 2024
Download
Short summary
Are machine learning models able to produce reliable rainfall-runoff predictions and add enough benefits that justify the effort to implement these methods? This study covers a large set of Australian catchments (almost 500) comparing deep learning and traditional model results. The deep learning model matched or exceeded conceptual model performance for more than two-thirds of the study catchments, indicating the general viability of these models in a variety of catchments conditions.