Towards understanding the influence of seasons on low-groundwater periods based on explainable machine learning

Wunsch, Andreas; Liesch, Tanja; Goldscheider, Nico

doi:https://doi.org/10.5194/hess-28-2167-2024

Articles | Volume 28, issue 9

https://doi.org/10.5194/hess-28-2167-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-28-2167-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 28, issue 9

Research article

|

17 May 2024

Research article |

| 17 May 2024

Towards understanding the influence of seasons on low-groundwater periods based on explainable machine learning

Andreas Wunsch, Tanja Liesch, and Nico Goldscheider

Download

Final revised paper (published on 17 May 2024)
Preprint (discussion started on 18 Dec 2023)
Supplement to the preprint

Interactive discussion

Status: closed

RC1:
'Comment on hess-2023-284', Jacopo Boaga, 22 Dec 2023

The paper concerns explainable machine learning to explore the influence of seasons in groundwater. Authors use example from a dataset in Germany and reach interesting conclusions about the role of seasonal characteristics in water storage resources. The paper is well written, figures are clear and so is the method. Reference are complete and conclusions are fully supported by the analysis. The results are of interest for the readers of HESS, since the proposed method opens new perspectives for a wider application. I encourage the publication of this relevant case study.

Citation: https://doi.org/10.5194/hess-2023-284-RC1
- AC1: 'Reply on RC1', Andreas Wunsch, 03 Jan 2024
  
  On behalf of all authors I thank Jacopo Boaga for this very fast and supportive comment on our preprint. We are happy to read that a publication is encouraged.
  
  Citation: https://doi.org/10.5194/hess-2023-284-AC1
RC2:
'Comment on hess-2023-284', Bastian Waldowski, 12 Mar 2024

Dear all,
Attached you find a pdf with my review. I hope these comments are helpful.
Best regards,

Bastian Waldowski

Citation: https://doi.org/10.5194/hess-2023-284-RC2
- AC2: 'Reply on RC2', Andreas Wunsch, 19 Mar 2024
  
  Thank you for your comments. Please find our detailed answers in the attached file.
  
  Citation: https://doi.org/10.5194/hess-2023-284-AC2

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload

ED: Publish subject to minor revisions (further review by editor) (09 Apr 2024) by Nunzio Romano

AR by Andreas Wunsch on behalf of the Authors (10 Apr 2024) Author's response Author's tracked changes Manuscript

ED: Publish as is (12 Apr 2024) by Nunzio Romano

AR by Andreas Wunsch on behalf of the Authors (15 Apr 2024)

Short summary

Seasons have a strong influence on groundwater levels, but relationships are complex and partly unknown. Using data from wells in Germany and an explainable machine learning approach, we showed that summer precipitation is the key factor that controls the severeness of a low-water period in fall; high summer temperatures do not per se cause stronger decreases. Preceding winters have only a minor influence on such low-water periods in general.