Preprints
https://doi.org/10.5194/egusphere-2024-114
https://doi.org/10.5194/egusphere-2024-114
09 Feb 2024
 | 09 Feb 2024

2001–2022 global gross primary productivity dataset using an ensemble model based on random forest

Xin Chen, Tiexi Chen, Xiaodong Li, Yuanfang Chai, Shengjie Zhou, Renjie Guo, and Jie Dai

Abstract. The continuous advancement of remote sensing technology has been instrumental in improving models for estimating terrestrial gross primary productivity (GPP). However, challenges arise from inconsistent spatial distributions and interannual variations in GPP datasets, impeding our comprehensive understanding of the entire terrestrial carbon cycle. In contrast to previous models relying on remote sensing and environmental variables, we developed a an ensemble model based on random forest named GPPERF. This model utilized the GPP outputs from established remote sensing-based models (EC-LUE, GPP-kNDVI, GPP-NIRv, Revised-EC-LUE) as inputs for GPP estimations. GPPERF demonstrated significant effectiveness by explaining 83.7 % of the monthly variation in GPP across 171 sites. This performance surpassed the selected remote sensing models (72.4 %–77.1 %) and an independent random forest model using remote sensing and environmental variables (77.7 %). Over the period from 2001 to 2022, the global estimated GPP value using the ensemble model based on random forest was 131.2 PgC yr-1, exhibiting a trend of 0.45 PgC yr-2. Furthermore, evaluation results utilizing flux sites from ChinaFlux indicated that the dateset exhibited good generalization. In summary, the machine learning-based ensemble method helps to reduce the uncertainty in the estimation of a single remote sensing model and provides a more reliable estimation of global GPP.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.

Journal article(s) based on this preprint

02 Oct 2024
A 2001–2022 global gross primary productivity dataset using an ensemble model based on the random forest method
Xin Chen, Tiexi Chen, Xiaodong Li, Yuanfang Chai, Shengjie Zhou, Renjie Guo, and Jie Dai
Biogeosciences, 21, 4285–4300, https://doi.org/10.5194/bg-21-4285-2024,https://doi.org/10.5194/bg-21-4285-2024, 2024
Short summary
Xin Chen, Tiexi Chen, Xiaodong Li, Yuanfang Chai, Shengjie Zhou, Renjie Guo, and Jie Dai

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-114', Anonymous Referee #1, 06 Mar 2024
    • AC1: 'Reply on RC1', Tiexi Chen, 07 Apr 2024
  • RC2: 'Comment on egusphere-2024-114', Anonymous Referee #2, 12 Mar 2024
    • AC2: 'Reply on RC2', Tiexi Chen, 07 Apr 2024

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-114', Anonymous Referee #1, 06 Mar 2024
    • AC1: 'Reply on RC1', Tiexi Chen, 07 Apr 2024
  • RC2: 'Comment on egusphere-2024-114', Anonymous Referee #2, 12 Mar 2024
    • AC2: 'Reply on RC2', Tiexi Chen, 07 Apr 2024

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
ED: Reconsider after major revisions (24 Apr 2024) by Anja Rammig
AR by Tiexi Chen on behalf of the Authors (25 Apr 2024)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (29 Apr 2024) by Anja Rammig
RR by Anonymous Referee #1 (08 May 2024)
ED: Reconsider after major revisions (04 Jun 2024) by Anja Rammig
AR by Tiexi Chen on behalf of the Authors (08 Jun 2024)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (05 Jul 2024) by Anja Rammig
RR by Anonymous Referee #1 (10 Jul 2024)
ED: Reconsider after major revisions (17 Jul 2024) by Anja Rammig
AR by Tiexi Chen on behalf of the Authors (20 Jul 2024)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (26 Jul 2024) by Anja Rammig
RR by Anonymous Referee #1 (12 Aug 2024)
ED: Publish subject to minor revisions (review by editor) (15 Aug 2024) by Anja Rammig
AR by Tiexi Chen on behalf of the Authors (15 Aug 2024)  Author's response   Author's tracked changes   Manuscript 
ED: Publish as is (16 Aug 2024) by Anja Rammig
AR by Tiexi Chen on behalf of the Authors (17 Aug 2024)  Manuscript 

Journal article(s) based on this preprint

02 Oct 2024
A 2001–2022 global gross primary productivity dataset using an ensemble model based on the random forest method
Xin Chen, Tiexi Chen, Xiaodong Li, Yuanfang Chai, Shengjie Zhou, Renjie Guo, and Jie Dai
Biogeosciences, 21, 4285–4300, https://doi.org/10.5194/bg-21-4285-2024,https://doi.org/10.5194/bg-21-4285-2024, 2024
Short summary
Xin Chen, Tiexi Chen, Xiaodong Li, Yuanfang Chai, Shengjie Zhou, Renjie Guo, and Jie Dai
Xin Chen, Tiexi Chen, Xiaodong Li, Yuanfang Chai, Shengjie Zhou, Renjie Guo, and Jie Dai

Viewed

Total article views: 581 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
414 134 33 581 67 17 23
  • HTML: 414
  • PDF: 134
  • XML: 33
  • Total: 581
  • Supplement: 67
  • BibTeX: 17
  • EndNote: 23
Views and downloads (calculated since 09 Feb 2024)
Cumulative views and downloads (calculated since 09 Feb 2024)

Viewed (geographical distribution)

Total article views: 569 (including HTML, PDF, and XML) Thereof 569 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 02 Oct 2024
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
We provides an ensemble model-based GPP dataset (ERF_GPP) that explains 83.7 % of the monthly variation in GPP across 171 sites, higher than other single remote sensing model. In addition, ERF_GPP improves the phenomenon of “high value underestimation and low value overestimation” in GPP estimation to some extent. Overall, ERF_GPP provides a more reliable estimate of global GPP and will facilitate further development of carbon cycle research.