Global hydro-climatic biomes identified via multitask learning

Papagiannopoulou, Christina; Miralles, Diego G.; Demuzere, Matthias; Verhoest, Niko E. C.; Waegeman, Willem

doi:https://doi.org/10.5194/gmd-11-4139-2018

Articles | Volume 11, issue 10

Geosci. Model Dev., 11, 4139–4153, 2018

https://doi.org/10.5194/gmd-11-4139-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Geosci. Model Dev., 11, 4139–4153, 2018

https://doi.org/10.5194/gmd-11-4139-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 11, issue 10

Model evaluation paper 12 Oct 2018

Model evaluation paper | 12 Oct 2018

Global hydro-climatic biomes identified via multitask learning

Christina Papagiannopoulou et al.

Supplement

https://doi.org/10.5194/gmd-11-4139-2018-supplement

Model code and software

Hydro-Climatic biomes: a multi-task learning approach. Papagiannopoulou, C., Miralles, D. G., Demuzere, M., Verhoest, N. E. C., and Waegeman, W. https://doi.org/10.5281/zenodo.1241047

Short summary

Common global land cover and climate classifications are based on vegetation–climatic characteristics derived from observational data, ignoring the interaction between the local climate and biome. Here, we model the interplay between vegetation and local climate by discovering spatial relationships among different locations. The resulting global hydro-climatic biomes correspond to regions of coherent climate–vegetation interactions that agree well with traditional global land cover maps.