Preprints
https://doi.org/10.5194/egusphere-2024-114
https://doi.org/10.5194/egusphere-2024-114
09 Feb 2024
 | 09 Feb 2024
Status: this preprint is open for discussion.

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.

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

Status: open (until 27 Mar 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
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: 168 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
128 34 6 168 20 4 5
  • HTML: 128
  • PDF: 34
  • XML: 6
  • Total: 168
  • Supplement: 20
  • BibTeX: 4
  • EndNote: 5
Views and downloads (calculated since 09 Feb 2024)
Cumulative views and downloads (calculated since 09 Feb 2024)

Viewed (geographical distribution)

Total article views: 161 (including HTML, PDF, and XML) Thereof 161 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 04 Mar 2024
Download
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.