Causality guided machine learning model on wetland CH4 emissions across global wetlands
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
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; Jurasinski, Gerald; Koebsch, Franziska; Campbell, David; Schmid, Hans Peter; Lohila, Annalea; Goeckede, Mathias; Nilsson, Mats B.; Friborg, Thomas; Jansen, Joachim; Zona, Donatella; Euskirchen, Eugenie; Ward, Eric J.; Bohrer, Gil; Jin, Zhenong; Liu, Licheng; Iwata, Hiroki; Goodrich, Jordan; Jackson, Robert.
I: Agricultural and Forest Meteorology, Bind 324, 109115, 2022.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Causality guided machine learning model on wetland CH4 emissions across global wetlands
AU - Yuan, Kunxiaojia
AU - Zhu, Qing
AU - Li, Fa
AU - Riley, William J.
AU - Torn, Margaret
AU - Chu, Housen
AU - McNicol, Gavin
AU - Chen, Min
AU - Knox, Sara
AU - Delwiche, Kyle
AU - Wu, Huayi
AU - Baldocchi, Dennis
AU - Ma, Hongxu
AU - Desai, Ankur R.
AU - Chen, Jiquan
AU - Sachs, Torsten
AU - Ueyama, Masahito
AU - Sonnentag, Oliver
AU - Helbig, Manuel
AU - Tuittila, Eeva-Stiina
AU - Jurasinski, Gerald
AU - Koebsch, Franziska
AU - Campbell, David
AU - Schmid, Hans Peter
AU - Lohila, Annalea
AU - Goeckede, Mathias
AU - Nilsson, Mats B.
AU - Friborg, Thomas
AU - Jansen, Joachim
AU - Zona, Donatella
AU - Euskirchen, Eugenie
AU - Ward, Eric J.
AU - Bohrer, Gil
AU - Jin, Zhenong
AU - Liu, Licheng
AU - Iwata, Hiroki
AU - Goodrich, Jordan
AU - Jackson, Robert
N1 - Publisher Copyright: © 2022
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Causal inference
KW - Eddy covariance CH emission
KW - Machine learning
KW - Wetlands
U2 - 10.1016/j.agrformet.2022.109115
DO - 10.1016/j.agrformet.2022.109115
M3 - Journal article
AN - SCOPUS:85135914716
VL - 324
JO - Agricultural and Forest Meteorology
JF - Agricultural and Forest Meteorology
SN - 0168-1923
M1 - 109115
ER -
ID: 323990096