Using Shapley additive explanations to interpret extreme gradient boosting predictions of grassland degradation in Xilingol, China

Batunacun,; Wieland, Ralf; Lakes, Tobia; Nendel, Claas

doi:https://doi.org/10.5194/gmd-14-1493-2021

Articles | Volume 14, issue 3

https://doi.org/10.5194/gmd-14-1493-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-14-1493-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 14, issue 3

Model evaluation paper

|

16 Mar 2021

Model evaluation paper |

| 16 Mar 2021

Using Shapley additive explanations to interpret extreme gradient boosting predictions of grassland degradation in Xilingol, China

Batunacun, Ralf Wieland, Tobia Lakes, and Claas Nendel

Download

Final revised paper (published on 16 Mar 2021)
Supplement to the final revised paper
Preprint (discussion started on 09 Jun 2020)
Supplement to the preprint

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

SC1: 'executive editor comment on gmd-2020-59', Astrid Kerkweg, 22 Jun 2020
- SC2: 'Python script DOI', Batunacun Ba, 22 Jul 2020
RC1: 'Review Report RN1', Anonymous Referee #1, 14 Jul 2020
- SC3: 'Response to comments', Batunacun Ba, 06 Aug 2020
  - RC2: 'Can you share the updated manuscript?', Anonymous Referee #1, 06 Aug 2020
    - AC2: 'Share the final manuscript', Batunacun Ba, 26 Oct 2020
RC3: 'Review of gmd-2020-59', Anonymous Referee #2, 28 Sep 2020
- AC1: 'Response to comments', Batunacun Ba, 26 Oct 2020

Peer-review completion

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

AR by Katja Gänger on behalf of the Authors (28 Oct 2020) Author's response

ED: Publish subject to technical corrections (10 Nov 2020) by David Topping

AR by Batunacun Ba on behalf of the Authors (18 Nov 2020) Author's response Manuscript

Short summary

Extreme gradient boosting (XGBoost) can provide alternative insights that conventional land-use models are unable to generate. Shapley additive explanations (SHAP) can interpret the results of the purely data-driven approach. XGBoost achieved similar and robust simulation results. SHAP values were useful for analysing the complex relationship between the different drivers of grassland degradation.