Articles | Volume 26, issue 19
Research article
 | Highlight paper
11 Oct 2022
Research article | Highlight paper |  | 11 Oct 2022

Improving hydrologic models for predictions and process understanding using neural ODEs

Marvin Höge, Andreas Scheidegger, Marco Baity-Jesi, Carlo Albert, and Fabrizio Fenicia


Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on hess-2022-56', Juan Pablo Carbajal, 11 Apr 2022
    • AC1: 'Reply on CC1', Marvin Höge, 16 Jun 2022
  • RC1: 'Comment on hess-2022-56', Andreas Wunsch, 07 May 2022
    • AC2: 'Reply on RC1', Marvin Höge, 16 Jun 2022
  • RC2: 'Comment on hess-2022-56', Mr Miyuru Gunathilake, 20 May 2022
    • AC3: 'Reply on RC2', Marvin Höge, 16 Jun 2022

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
ED: Publish subject to minor revisions (further review by editor) (11 Aug 2022) by Marnik Vanclooster
AR by Marvin Höge on behalf of the Authors (21 Aug 2022)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (11 Sep 2022) by Marnik Vanclooster
Executive editor
This is a paper demonstrating the added value of hybrid modeling approaches for modeling hydrological features (flow and internal states). The paper is well written and will be sent out for a detailed scientific review. The combination of ANN with ODE-based hydrological models is a good way forward to construct hybrid modeling approaches. It is a significant step forward compared to the current state of the art.
Short summary
Neural ODEs fuse physics-based models with deep learning: neural networks substitute terms in differential equations that represent the mechanistic structure of the system. The approach combines the flexibility of machine learning with physical constraints for inter- and extrapolation. We demonstrate that neural ODE models achieve state-of-the-art predictive performance while keeping full interpretability of model states and processes in hydrologic modelling over multiple catchments.