Articles | Volume 18, issue 5
https://doi.org/10.5194/essd-18-3507-2026
https://doi.org/10.5194/essd-18-3507-2026
Data description article
 | Highlight paper
 | 
22 May 2026
Data description article | Highlight paper |  | 22 May 2026

Machine-learning-based estimates of global natural vegetated wetland methane emissions (2000–2025)

Mengze Li, Robert B. Jackson, Marielle Saunois, Philippe Ciais, Ben Poulter, Josep G. Canadell, Prabir K. Patra, Hanqin Tian, Zhen Zhang, Etienne Fluet-Chouinard, Zutao Ouyang, Ting Zhang, David J. Beerling, Dmitry A. Belikov, Philippe Bousquet, Danilo Custodio, Naveen Chandra, Xinyu Dou, Nicola Gedney, Peter O. Hopcroft, Alison M. Hoyt, Kazuhito Ichii, Akihito Ito, Atul K. Jain, Katherine Jensen, Fortunat Joos, Thomas Kleinen, Masayuki Kondo, Fa Li, Tingting Li, Xiangyu Liu, Shamil Maksyutov, Avni Malhotra, Adrien Martinez, Kyle McDonald, Joe R. Melton, Jurek Müller, Yosuke Niwa, Shufen Pan, Shushi Peng, Changhui Peng, Zhangcai Qin, Peter Raymond, William Riley, Arjo Segers, Rona L. Thompson, Aki Tsuruta, Yi Xi, Kunxiaojia Yuan, Wenxin Zhang, Bo Zheng, Qing Zhu, Qiuan Zhu, and Qianlai Zhuang

Data sets

ERA5 monthly averaged data on single levels from 1940 to present Copernicus Climate Change Service https://doi.org/10.24381/cds.f17050d7

Global natural wetland methane emissions (2000-2025) M. Li et al. https://doi.org/10.5281/zenodo.18870108

Download
Editorial statement
This article describes a new methodology to evaluate CH4 emissions from wetlands on a global scale, providing a scalable capacity to frequently update global emission estimates, such as those presented in the Global Carbon Budget.
Short summary
We proposed a framework that combines machine-learning and climate data to predict global natural vegetated wetland methane emissions for 2000–2025. We found that although total global emissions remained stable in the post-2020s, Northern Hemisphere emissions surged whilst tropical emissions fell. This approach allows us to rapidly monitor emissions and provides early warnings for climate impacts.
Share
Altmetrics
Final-revised paper
Preprint