Using deep learning to assimilate sun-induced fluorescence satellite observations in the ISBA land surface model

Vanderbecken, Pierre; Vural, Jasmin; Rojas-Muñoz, Oscar; Garrigues, Sébastien; Bonan, Bertrand; Bacour, Cédric; Rascher, Uwe; Siegmann, Bastian; de Rosnay, Patricia; Calvet, Jean-Christophe

doi:10.5194/bg-23-6687-2026

Articles | Volume 23, issue 18

https://doi.org/10.5194/bg-23-6687-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/bg-23-6687-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 23, issue 18

Research article

|

23 Sep 2026

Research article |

| 23 Sep 2026

Using deep learning to assimilate sun-induced fluorescence satellite observations in the ISBA land surface model

Pierre Vanderbecken, Jasmin Vural, Oscar Rojas-Muñoz, Sébastien Garrigues, Bertrand Bonan, Cédric Bacour, Uwe Rascher, Bastian Siegmann, Patricia de Rosnay, and Jean-Christophe Calvet

Supplement

https://doi.org/10.5194/bg-23-6687-2026-supplement

Data sets

WP4 - supplementary data - Using deep learning to assimilate sun-induced fluorescence satellite observations in the ISBA land surface model: Datasets P. J. Vanderbecken https://doi.org/10.5281/zenodo.18668100

Model code and software

WP4 - supplementary data - Using deep learning to assimilate sun-induced fluorescence satellite observations in the ISBA land surface model: model P. J. Vanderbecken https://doi.org/10.5281/zenodo.18669437

Download

Article (4408 KB)
Full-text XML

Short summary

New satellite observations are used to improve our understanding of regional-scale vegetation. Innovative artificial intelligence methods are employed to combine the available information. The effectiveness of this approach is evaluated using independent observations. The results show that agricultural practices such as irrigation can be modelled more accurately.