Top-down approaches

Thompson, Rona L.; Chevallier, F.; Maksyutov, Shamil; Patra, Prabir K.; Bowman, K. W.

doi:10.1016/b978-0-12-814952-2.00008-3

Cited by 1 publication

(1 citation statement)

References 184 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former uses a combination of human activity data and inventoryspecific emission factors, process-based models, or remote-sensing approaches to estimate the fluxes (Poulter et al, 2022). The latter formulates it as an inverse problem, in which statistical methods or optimization approaches are used to invert the CO 2 transport process to find the optimal surface fluxes that best match the observed atmospheric CO 2 concentra-tion (Thompson et al, 2022). The link between carbon dioxide concentration and surface carbon fluxes is established through atmospheric transport models (Community, 2021;Grell et al, 2005;Emmons et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

An Automatic Differentiation Method for Surface Carbon Flux Inversion

Yao

Chen

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

We attempt, for the first time, to estimate the surface carbon flux by the method of automatic differentiation. The atmospheric transport model is developed using a deep learning framework and is validated against standard approaches. Depends on the built-in automatic differentiation feature of the deep learning framework, the system derivatives/gradients are readily available without any extra effort. We then formulate the surface carbon flux estimation as an inverse problem using the variational approach, driven by back-propagated objective gradients. The feasibility of the automatic differentiation method is demonstrated in identical-twin observing system simulation experiments (OSSEs). The proposed framework shows favorable accuracy and great efficiency in both fully and partially observable scenarios. The present study establishes a link between machine learning frameworks and general data assimilation or inverse modeling problems, and the promising results encourage more investigations in incorporating machine learning techniques in inverse carbon modeling.

show abstract

Section: Introductionmentioning

confidence: 99%