Preprints
https://doi.org/10.5194/egusphere-2024-2147
https://doi.org/10.5194/egusphere-2024-2147
30 Jul 2024
 | 30 Jul 2024

Analyzing the generalization capabilities of hybrid hydrological models for extrapolation to extreme events

Eduardo Acuna Espinoza, Ralf Loritz, Frederik Kratzert, Daniel Klotz, Martin Gauch, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret

Abstract. Data-driven techniques have shown the potential to outperform process-based models for rainfall-runoff simulation. Recently, hybrid models, which combine data-driven methods with process-based approaches, have been proposed to leverage the strengths of both methodologies, aiming to enhance simulation accuracy while maintaining certain interpretability. Expanding the set of test cases to evaluate hybrid models under different conditions, we test their generalization capabilities for extreme hydrological events, comparing their performance against Long Short-Term Memory (LSTM) networks and process based models. Our results indicate that hybrid models show similar performance as LSTM networks for most cases. However, hybrid models reported slightly lower errors in the most extreme cases, and were able to produce higher peak discharges.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Eduardo Acuna Espinoza, Ralf Loritz, Frederik Kratzert, Daniel Klotz, Martin Gauch, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on egusphere-2024-2147', Chaopeng Shen, 22 Aug 2024
    • AC1: 'Reply on CC1', Eduardo Acuna, 09 Sep 2024
      • CC3: 'Reply on AC1', Chaopeng Shen, 19 Sep 2024
        • AC3: 'Reply on CC3', Eduardo Acuna, 04 Oct 2024
  • CC2: 'Comment on egusphere-2024-2147', John Ding, 30 Aug 2024
    • AC2: 'Reply on CC2', Eduardo Acuna, 09 Sep 2024
  • RC1: 'Comment on egusphere-2024-2147', Basil Kraft, 05 Sep 2024
    • AC4: 'Reply on RC1', Eduardo Acuna, 04 Oct 2024
  • RC2: 'Comment on egusphere-2024-2147', Shijie Jiang, 06 Oct 2024
    • AC5: 'Reply on RC2', Eduardo Acuna, 15 Oct 2024
Eduardo Acuna Espinoza, Ralf Loritz, Frederik Kratzert, Daniel Klotz, Martin Gauch, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret
Eduardo Acuna Espinoza, Ralf Loritz, Frederik Kratzert, Daniel Klotz, Martin Gauch, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret

Viewed

Total article views: 902 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
529 170 203 902 3 4
  • HTML: 529
  • PDF: 170
  • XML: 203
  • Total: 902
  • BibTeX: 3
  • EndNote: 4
Views and downloads (calculated since 30 Jul 2024)
Cumulative views and downloads (calculated since 30 Jul 2024)

Viewed (geographical distribution)

Total article views: 972 (including HTML, PDF, and XML) Thereof 972 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2024
Download
Short summary
Data-driven techniques have shown the potential to outperform process-based models in rainfall-runoff simulations. Hybrid models, combining both approaches, aim to enhance accuracy and maintain interpretability. Expanding the set of test cases to evaluate hybrid models under different conditions we test their generalization capabilities for extreme hydrological events.