Skip to main content
Research article - Peer-reviewed, 2022

Causality guided machine learning model on wetland CH4 emissions across global wetlands

Yuan, Kunxiaojia; Zhu, Qing; Li, Fa; Riley, William J.; Torn, Margaret; Chu, Housen; McNicol, Gavin; Chen, Min; Knox, Sara; Delwiche, Kyle; Wu, Huayi; Baldocchi, Dennis; Ma, Hongxu; Desai, Ankur R.; Chen, Jiquan; Sachs, Torsten; Ueyama, Masahito; Sonnentag, Oliver; Helbig, Manuel; Tuittila, Eeva-Stiina;
Show more authors

Abstract

Wetland CH4 emissions are among the most uncertain components of the global CH4 budget. The complex nature of wetland CH4 processes makes it challenging to identify causal relationships for improving our understanding and predictability of CH4 emissions. In this study, we used the flux measurements of CH4 from eddy covariance towers (30 sites from 4 wetlands types: bog, fen, marsh, and wet tundra) to construct a causality-constrained machine learning (ML) framework to explain the regulative factors and to capture CH4 emissions at sub -seasonal scale. We found that soil temperature is the dominant factor for CH4 emissions in all studied wetland types. Ecosystem respiration (CO2) and gross primary productivity exert controls at bog, fen, and marsh sites with lagged responses of days to weeks. Integrating these asynchronous environmental and biological causal relationships in predictive models significantly improved model performance. More importantly, modeled CH4 emissions differed by up to a factor of 4 under a +1C warming scenario when causality constraints were considered. These results highlight the significant role of causality in modeling wetland CH(4 )emissions especially under future warming conditions, while traditional data-driven ML models may reproduce observations for the wrong reasons. Our proposed causality-guided model could benefit predictive modeling, large-scale upscaling, data gap-filling, and surrogate modeling of wetland CH4 emissions within earth system land models.

Keywords

Eddy covariance CH4 emission; Wetlands; Causal inference; Machine learning

Published in

Agricultural and Forest Meteorology

2022, volume: 324, article number: 109115
Publisher: ELSEVIER

Authors' information

Yuan, Kunxiaojia
Lawrence Berkeley National Laboratory (Berkeley Lab)
Zhu, Qing
Lawrence Berkeley National Laboratory (Berkeley Lab)
Li, Fa
Lawrence Berkeley National Laboratory (Berkeley Lab)
Li, Fa
University of Wisconsin Madison
Riley, William J.
Lawrence Berkeley National Laboratory (Berkeley Lab)
Torn, Margaret S.
Lawrence Berkeley National Laboratory
Chu, Housen
Lawrence Berkeley Natl Lab
McNicol, Gavin
University of Illinois Chicago
Chen, Min
University of Wisconsin Madison
Knox, Sara
University of British Columbia
Delwiche, Kyle
University of California Berkeley
Wu, Huayi
Wuhan University
Baldocchi, Dennis
University of California Berkeley
Ma, Hongxu
University of California Berkeley
Desai, Ankur R.
University of Wisconsin Madison
Chen, Jiquan
Michigan State University
Sachs, Torsten
Helmholtz-Center Potsdam GFZ German Research Center for Geosciences
Ueyama, Masahito
Osaka Metropolitan University
Sonnentag, Oliver
Lawrence Berkeley National Laboratory (Berkeley Lab)
Helbig, Manuel
Dalhousie University
Show more authors

UKÄ Subject classification

Meteorology and Atmospheric Sciences
Physical Geography
Climate Research

Publication Identifiers

DOI: https://doi.org/10.1016/j.agrformet.2022.109115

URI (permanent link to this page)

https://res.slu.se/id/publ/119351