Focal-TSMP: deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation

Shams Eddin, Mohamad Hakam; Gall, Juergen

doi:https://doi.org/10.5194/gmd-17-2987-2024

Articles | Volume 17, issue 7

https://doi.org/10.5194/gmd-17-2987-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-17-2987-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 17, issue 7

Model description paper

|

16 Apr 2024

Model description paper |

| 16 Apr 2024

Focal-TSMP: deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation

Mohamad Hakam Shams Eddin and Juergen Gall

Data sets

Focal-TSMP: Deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation Mohamad Hakam Shams Eddin and Juergen Gall https://doi.org/10.5281/zenodo.10008814

Pan-european, physically consistent simulations from groundwater to the atmosphere with the Terrestrial Systems Modeling Platform, TerrSysMP (1989-2018 daily time-series) Carina Furusho et al. https://doi.org/10.1594/PANGAEA.901823

Model code and software

Focal-TSMP: Deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation Mohamad Hakam Shams Eddin and Juergen Gall https://doi.org/10.5281/zenodo.10015048

Focal-TSMP: Deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation Mohamad Hakam Shams Eddin https://github.com/HakamShams/Focal_TSMP

Video abstract

Focal-TSMP Mohamad Hakam Shams Eddin https://doi.org/10.5446/66878

Short summary

In this study, we use deep learning and a climate simulation to predict the vegetation health as it would be observed from satellites. We found that the developed model can help to identify regions with a high risk of agricultural drought. The main applications of this study are to estimate vegetation products for periods where no satellite data are available and to forecast the future vegetation response to climate change based on climate scenarios.