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

Kunxiaojia Yuan; Qing Zhu; Fa Li; William J. Riley; Margaret Torn; Housen Chu; Gavin McNicol; Mingshu Chen; Sara Knox; Kyle B. Delwiche; Huayi Wu; Dennis Baldocchi; Hongxu Ma; Ankur R. Desai; Jiquan Chen; Torsten Sachs; Masahito Ueyama; Oliver Sonnentag; Manuel Helbig; Eeva-Stiina Tuittila; Gerald Jurasinski; Franziska Koebsch; David I. Campbell; Hans Peter Schmid; Annalea Lohila; Mathias Goeckede; Mats B. Nilsson; Thomas Friborg; Joachim Jansen; Donatella Zona; Eugenie S. Euskirchen; Eric Ward; Gil Bohrer; Zhenong Jin; Licheng Liu; Hiroki Iwata; Jordan P. Goodrich; Robert B. Jackson

doi:10.1016/j.agrformet.2022.109115

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

Agricultural and Forest Meteorology

By: Kunxiaojia Yuan, Qing Zhu, Fa Li, William J. Riley, Margaret Torn, Housen Chu, Gavin McNicol, Mingshu Chen, Sara Knox, Kyle B. Delwiche, Huayi Wu, Dennis Baldocchi, Hongxu Ma, Ankur R. Desai, Jiquan Chen, Torsten Sachs, Masahito Ueyama, Oliver Sonnentag, Manuel Helbig, Eeva-Stiina Tuittila, Gerald Jurasinski, Franziska Koebsch, David I. Campbell, Hans Peter Schmid, Annalea Lohila, Mathias Goeckede, Mats B. Nilsson, Thomas Friborg, Joachim Jansen, Donatella Zona, Eugenie S. Euskirchen, Eric Ward, Gil Bohrer, Zhenong Jin, Licheng Liu, Hiroki Iwata, Jordan P. Goodrich, and Robert B. Jackson

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

Links

More information: Publisher Index Page (via DOI)
Open Access Version: Publisher Index Page
Download citation as: RIS | Dublin Core

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 +1°C warming scenario when causality constraints were considered. These results highlight the significant role of causality in modeling wetland CH₄ 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.

Additional publication details
Publication type	Article
Publication Subtype	Journal Article
Title	Causality guided machine learning model on wetland CH4 emissions across global wetlands
Series title	Agricultural and Forest Meteorology
DOI	10.1016/j.agrformet.2022.109115
Volume	324
Year Published	2022
Language	English
Publisher	Elsevier
Contributing office(s)	Wetland and Aquatic Research Center
Description	109115, 10 p.
Google Analytic Metrics	Metrics page