Articles | Volume 28, issue 3
Research article
07 Feb 2024
Research article |  | 07 Feb 2024

On the need for physical constraints in deep learning rainfall–runoff projections under climate change: a sensitivity analysis to warming and shifts in potential evapotranspiration

Sungwook Wi and Scott Steinschneider


Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'When the rooster crows the sun rises', Daniel Klotz, 22 Aug 2023
    • RC4: 'Reply on RC1', Daniel Klotz, 03 Oct 2023
      • AC4: 'Reply on RC4', Sungwook Wi, 30 Oct 2023
    • AC1: 'Reply on RC1', Sungwook Wi, 29 Oct 2023
  • RC2: 'Comment on egusphere-2023-1744', Shijie Jiang, 12 Sep 2023
    • AC2: 'Reply on RC2', Sungwook Wi, 29 Oct 2023
  • RC3: 'Comment on egusphere-2023-1744', Larisa Tarasova, 13 Sep 2023
    • AC3: 'Reply on RC3', Sungwook Wi, 29 Oct 2023

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
ED: Publish subject to revisions (further review by editor and referees) (31 Oct 2023) by Ralf Loritz
AR by Sungwook Wi on behalf of the Authors (03 Nov 2023)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (07 Nov 2023) by Ralf Loritz
RR by Larisa Tarasova (04 Dec 2023)
RR by Shijie Jiang (09 Dec 2023)
RR by Daniel Klotz (09 Dec 2023)
ED: Publish subject to technical corrections (11 Dec 2023) by Ralf Loritz
AR by Sungwook Wi on behalf of the Authors (20 Dec 2023)  Author's response   Manuscript 
Short summary
We investigate whether deep learning (DL) models can produce physically plausible streamflow projections under climate change. We address this question by focusing on modeled responses to increases in temperature and potential evapotranspiration and by employing three DL and three process-based hydrological models. The results suggest that physical constraints regarding model architecture and input are necessary to promote the physical realism of DL hydrological projections under climate change.