Journal cover Journal topic
Geoscientific Model Development An interactive open-access journal of the European Geosciences Union
https://doi.org/10.5194/gmd-2018-92
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Model evaluation paper
25 Apr 2018
Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Geoscientific Model Development (GMD).
Global hydro-climatic biomes identified via multi-task learning
Christina Papagiannopoulou1, Diego G. Miralles2, Matthias Demuzere2, Niko E. C. Verhoest2, and Willem Waegeman1 1Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium
2Laboratory of Hydrology and Water Management, Ghent University, Belgium
Abstract. The most widely-used global land cover and climate classifications are based on vegetation characteristics and/or climatic conditions derived from observational data. However, these classification schemes do not directly stem from the interaction between the local climate and the biotic environment. In this work, we model the dynamic interplay between vegetation and local climate in order to delineate ecoregions that share a coherent response to hydro-climate variability. Our novel framework is based on a multi-task learning approach that discovers the spatial relationships among different locations by learning a low-dimensional representation of predictive structures. This low-dimensional representation is combined with a clustering algorithm that yields a classification of biomes with coherent behaviour. Experimental results using global observation-based data sets indicate that, without the need to prescribe any land cover information, our method is able to identify regions of coherent climate-vegetation interactions that agree well with the expectations derived from traditional global land cover maps. The resulting global hydro-climatic biomes can be used to analyse the anomalous behaviour of specific ecosystems in response to climate extremes and to benchmark climate-vegetation interactions in Earth system models.
Citation: Papagiannopoulou, C., Miralles, D. G., Demuzere, M., Verhoest, N. E. C., and Waegeman, W.: Global hydro-climatic biomes identified via multi-task learning, Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2018-92, in review, 2018.
Christina Papagiannopoulou et al.
Christina Papagiannopoulou et al.
Christina Papagiannopoulou et al.

Viewed

Total article views: 222 (including HTML, PDF, and XML)

HTML PDF XML Total Supplement BibTeX EndNote
170 47 5 222 10 5 3

Views and downloads (calculated since 25 Apr 2018)

Cumulative views and downloads (calculated since 25 Apr 2018)

Viewed (geographical distribution)

Total article views: 222 (including HTML, PDF, and XML)

Thereof 219 with geography defined and 3 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 23 May 2018
Publications Copernicus
Download
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.
Common global land cover and climate classifications are based on vegetation-climatic...
Share