Preprints
https://doi.org/10.5194/gmd-2021-271
https://doi.org/10.5194/gmd-2021-271

Submitted as: development and technical paper 11 Aug 2021

Submitted as: development and technical paper | 11 Aug 2021

Review status: this preprint is currently under review for the journal GMD.

Predicting Global Terrestrial Biomes with Convolutional Neural Network

Hisashi Sato1 and Takeshi Ise2 Hisashi Sato and Takeshi Ise
  • 1Research Institute for Global Change (RIGC), Japan Agency for Marine-Earth Science and Technology (JAMSTEC), Yokohama, 236-0001, JAPAN
  • 2Field Science Education and Research Center (FSERC), Kyoto University, Kyoto, 606-8502, JAPAN

Abstract. A biome is a major regional ecological community characterized by distinctive life forms and principal plants. Many empirical schemes such as the Holdridge Life Zone (HLZ) system have been proposed and implemented to predict the global distribution of terrestrial biomes. Knowledge of physiological climatic limits has been employed to predict biomes, resulting in more precise simulation, however, this requires different sets of physiological limits for different vegetation classification schemes. Here, we demonstrate an accurate and practical method to construct empirical models for biome mapping: A convolutional neural network (CNN) was trained by an observation-based biome map, as well as images depicting air temperature and precipitation. The trained model accurately simulated a global map of current terrestrial biome distribution. Then, the trained model was applied to climate scenarios toward the end of the 21st century, predicting a significant shift in global biome distribution with rapid warming trends. Our results demonstrate that the proposed CNN approach can provide an efficient and objective method to generate preliminary estimations of the impact of climate change on biome distribution. Moreover, we anticipate that our approach could provide a basis for more general implementations to build empirical models of other climate-driven categorical phenomena.

Hisashi Sato and Takeshi Ise

Status: open (until 11 Oct 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CEC1: 'Comment on gmd-2021-271', Juan Antonio Añel, 14 Aug 2021 reply
    • AC1: 'Reply on CEC1', Hisashi Sato, 15 Aug 2021 reply
  • RC1: 'Comment on gmd-2021-271', Anonymous Referee #1, 20 Sep 2021 reply

Hisashi Sato and Takeshi Ise

Data sets

Sato and Ise (submitted) Open Data, version 3 Hisashi SATO, Takeshi ISE https://doi.org/10.5281/zenodo.4401233

Hisashi Sato and Takeshi Ise

Viewed

Total article views: 290 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
233 49 8 290 30 2 1
  • HTML: 233
  • PDF: 49
  • XML: 8
  • Total: 290
  • Supplement: 30
  • BibTeX: 2
  • EndNote: 1
Views and downloads (calculated since 11 Aug 2021)
Cumulative views and downloads (calculated since 11 Aug 2021)

Viewed (geographical distribution)

Total article views: 210 (including HTML, PDF, and XML) Thereof 210 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 Sep 2021
Download
Short summary
Accurately predicting global coverage of terrestrial biome is one of the earliest ecological concerns, and many empirical schemes have been proposed to characterize their relationship. Here, we demonstrate an accurate and practical method to construct empirical models for operational biome mapping via a convolutional neural network (CNN) approach.