A differentiable, physics-informed ecosystem modeling and  learning framework for large-scale inverse problems:  demonstration with photosynthesis simulations

Aboelyazeed, Doaa; Xu, Chonggang; Hoffman, Forrest M.; Liu, Jiangtao; Jones, Alex W.; Rackauckas, Chris; Lawson, Kathryn; Shen, Chaopeng

doi:https://doi.org/10.5194/bg-20-2671-2023

Articles | Volume 20, issue 13

https://doi.org/10.5194/bg-20-2671-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/bg-20-2671-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 20, issue 13

Research article

|

06 Jul 2023

Research article |

| 06 Jul 2023

A differentiable, physics-informed ecosystem modeling and learning framework for large-scale inverse problems: demonstration with photosynthesis simulations

Doaa Aboelyazeed, Chonggang Xu, Forrest M. Hoffman, Jiangtao Liu, Alex W. Jones, Chris Rackauckas, Kathryn Lawson, and Chaopeng Shen

Data sets

Leaf Gas Exchange Database Y.-S. Lin, B. Medlyn, R. Duursma, and J. Knauer https://bitbucket.org/gsglobal/leafgasexchange/src/master/

Model code and software

A differentiable ecosystem modeling framework for large-scale inverse problems D. Aboelyazeed, C. Xu, F. M. Hoffman, A. W. Jones, C. Rackauckas, K. E. Lawson, and C. Shen https://doi.org/10.5281/zenodo.8067204

Short summary

Photosynthesis is critical for life and has been affected by the changing climate. Many parameters come into play while modeling, but traditional calibration approaches face many issues. Our framework trains coupled neural networks to provide parameters to a photosynthesis model. Using big data, we independently found parameter values that were correlated with those in the literature while giving higher correlation and reduced biases in photosynthesis rates.