ML-SWAN-v1: a hybrid machine learning framework for the concentration prediction and discovery of transport pathways of surface water nutrients

Wang, Benya; Hipsey, Matthew R.; Oldham, Carolyn

doi:https://doi.org/10.5194/gmd-13-4253-2020

Articles | Volume 13, issue 9

https://doi.org/10.5194/gmd-13-4253-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-13-4253-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 9

Model evaluation paper

|

15 Sep 2020

Model evaluation paper |

| 15 Sep 2020

ML-SWAN-v1: a hybrid machine learning framework for the concentration prediction and discovery of transport pathways of surface water nutrients

Benya Wang, Matthew R. Hipsey, and Carolyn Oldham

Download

Final revised paper (published on 15 Sep 2020)
Supplement to the final revised paper
Preprint (discussion started on 06 Apr 2020)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Review comment on manuscript GMD-2020-4', Thu Huong Thi Hoang, 28 May 2020
- AC1: 'Author's Response', Benya Wang, 05 Jun 2020
RC2: 'Review Comment', Anonymous Referee #2, 02 Jun 2020
- AC2: 'Author's Response', Benya Wang, 06 Jun 2020

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Benya Wang on behalf of the Authors (06 Jul 2020)

ED: Publish as is (23 Jul 2020) by Thomas Poulet

AR by Benya Wang on behalf of the Authors (26 Jul 2020) Author's response Manuscript

Short summary

Surface water nutrients are essential to manage water quality, but it is hard to analyse trends. We developed a hybrid model and compared with other models for the prediction of six different nutrients. Our results showed that the hybrid model had significantly higher accuracy and lower prediction uncertainty for almost all nutrient species. The hybrid model provides a flexible method to combine data of varied resolution and quality and is accurate for the prediction of nutrient concentrations.