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

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

doi:https://doi.org/10.5194/bg-21-4285-2024

Articles | Volume 21, issue 19

https://doi.org/10.5194/bg-21-4285-2024

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

https://doi.org/10.5194/bg-21-4285-2024

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

Articles | Volume 21, issue 19

Research article

|

02 Oct 2024

Research article |

| 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

Supplement

https://doi.org/10.5194/bg-21-4285-2024-supplement

Data sets

2001-2022 global gross primary productivity dataset using an ensemble model based on random forest Xin Chen et al. https://doi.org/10.6084/m9.figshare.24417649

Download

Article (5690 KB)
Full-text XML

Short summary

We provide an ensemble-model-based GPP dataset (ERF_GPP) that explains 85.1 % of the monthly variation in GPP across 170 sites, which is higher than other GPP estimate models. 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.