KIT | KIT-Bibliothek | Impressum | Datenschutz

Causality guided machine learning model on wetland CH$_{4}$ 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; ... mehr

Abstract:

Wetland CH4 emissions are among the most uncertain components of the global CH$_{4}$ budget. The complex nature of wetland CH$_{4}$ processes makes it challenging to identify causal relationships for improving our understanding and predictability of CH$_{4}$ emissions. In this study, we used the flux measurements of CH$_{4}$ 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 CH$_{4}$ emissions at sub-seasonal scale. We found that soil temperature is the dominant factor for CH$_{4}$ emissions in all studied wetland types. Ecosystem respiration (CO$_{2}$) 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 CH$_{4}$ 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 CH$_{4}$ emissions especially under future warming conditions, while traditional data-driven ML models may reproduce observations for the wrong reasons. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000150395
Veröffentlicht am 08.09.2022
Originalveröffentlichung
DOI: 10.1016/j.agrformet.2022.109115
Scopus
Zitationen: 11
Web of Science
Zitationen: 11
Dimensions
Zitationen: 14
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Meteorologie und Klimaforschung – Atmosphärische Umweltforschung (IMK-IFU)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 09.2022
Sprache Englisch
Identifikator ISSN: 0168-1923, 1873-2240
KITopen-ID: 1000150395
HGF-Programm 12.11.31 (POF IV, LK 01) New observational systems and cross platform integration
Erschienen in Agricultural and Forest Meteorology
Verlag Elsevier
Band 324
Seiten Art.-Nr.: 109115
Nachgewiesen in Scopus
Web of Science
Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page