Preprints
https://doi.org/10.5194/egusphere-2023-1980
https://doi.org/10.5194/egusphere-2023-1980
15 Sep 2023
 | 15 Sep 2023

To Bucket or not to Bucket? Analyzing the performance and interpretability of hybrid hydrological models with dynamic parameterization

Eduardo Acuña Espinoza, Ralf Loritz, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret

Abstract. Hydrological hybrid models have been proposed as an option to combine the enhanced performance of deep learning methods with the interpretability of process-based models. Among the various hybrid methods available, the dynamic parameterization of conceptual models using LSTM networks has shown high potential. We explored this method further to evaluate specifically if the flexibility given by the dynamic parameterization overwrites the physical interpretability of the process-based part. We conducted our study using a subset of CAMELS-GB dataset. First, we show that the hybrid model can reach state-of-the-art performance, fully comparable with a regional LSTM, and surpassing the performance of conceptual models in the same area. We then modified the conceptual model structure to assess if the dynamic parameterization can compensate for structural deficiencies of the model. Our results demonstrated the ability of the deep learning method to effectively compensate for deficiencies and implausible model structures in the hydrological models. This indicates that the hydrological model did not give a strong enough regularization to drop the hybrid model's performance. A model selection based purely on the performance to predict streamflow, for this type of hybrid model, is hence not advisable. However, this does not entail that such hybrid models cannot be used to gain a better understanding of a hydrological system by studying other hydrological fluxes and states than discharge. Comparisons with external data, as well as the internal functioning of the hybrid model, reiterate that if a well-tested model architecture is combined with a LSTM, the deep learning model can learn to operate the process-based model in a consistent matter. In conclusion, this study demonstrated that hybrid models, if set up cautiously, can combine the enhanced performance of deep learning methods while maintaining good interpretability in the process-based part.

Eduardo Acuña Espinoza, Ralf Loritz, 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
  • RC1: 'Comment on egusphere-2023-1980', Anonymous Referee #1, 06 Oct 2023
    • AC1: 'Reply on RC1', Eduardo Acuna, 23 Oct 2023
  • RC2: 'Comment on egusphere-2023-1980', Grey Nearing, 13 Nov 2023
    • AC2: 'Reply on RC2', Eduardo Acuna, 04 Dec 2023
Eduardo Acuña Espinoza, Ralf Loritz, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret
Eduardo Acuña Espinoza, Ralf Loritz, Manuel Álvarez Chaves, Nicole Bäuerle, and Uwe Ehret

Viewed

Total article views: 732 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
492 212 28 732 18 18
  • HTML: 492
  • PDF: 212
  • XML: 28
  • Total: 732
  • BibTeX: 18
  • EndNote: 18
Views and downloads (calculated since 15 Sep 2023)
Cumulative views and downloads (calculated since 15 Sep 2023)

Viewed (geographical distribution)

Total article views: 728 (including HTML, PDF, and XML) Thereof 728 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Apr 2024
Download
Short summary
Hydrological hybrid models merge the performance of deep learning methods with the interpretability of process-based models. One hybrid approach is the dynamic parameterization of conceptual models using LSTM networks. We explored this method to evaluate if the flexibility given by LSTM overwrites the interpretability of the process-based part. We showed that if a well-tested model architecture is combined with an LSTM, the latter can learn to operate the process-based model consistently.