Preprints
https://doi.org/10.5194/gmd-2017-152
https://doi.org/10.5194/gmd-2017-152
Submitted as: model description paper
 | 
13 Jul 2017
Submitted as: model description paper |  | 13 Jul 2017
Status: this preprint has been withdrawn by the authors.

A map of global peatland distribution created using machine learning for use in terrestrial ecosystem and earth system models

Yuanqiao Wu, Ed Chan, Joe R. Melton, and Diana L. Verseghy

Abstract. Peatlands store large amounts of soil carbon and constitute an important component of the global carbon cycle. Accurate information on the global extent and distribution of peatlands is presently lacking but it important for earth system models (ESMs) to be able to simulate the effects of climate change on the global carbon balance. The most comprehensive peatland map produced to date is a qualitative presence/absence product. Here, we present a spatially continuous global map of peatland fractional coverage using the extremely randomized tree machine learning method suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model include spatially distributed climate data, soil data and topographical slopes. Available maps of peatland fractional coverage for Canada and West Siberia were used along with a proxy for non-peatland areas to train and test the statistical model. Regions where the peatland fraction is expected to be zero were estimated from a map of topsoil organic carbon content below a threshold value of 13 kg/m2. The modelled coverage of peatlands yields a root mean square error of 4 % and a coefficient of determination of 0.91 for the 10,978 tested 0.5 degree grid cells. We then generated a complete global peatland fractional coverage map. In comparison with earlier qualitative estimates, our global modelled peatland map is able to reproduce peatland distributions in places remote from the training areas and capture peatland hot spots in both boreal and tropical regions, as well as in the southern hemisphere. Additionally we demonstrate that our machine-learning method has greater skill than solely setting peatland areas based on histosols from a soil database.

This preprint has been withdrawn.

Yuanqiao Wu, Ed Chan, Joe R. Melton, and Diana L. Verseghy

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
Yuanqiao Wu, Ed Chan, Joe R. Melton, and Diana L. Verseghy
Yuanqiao Wu, Ed Chan, Joe R. Melton, and Diana L. Verseghy

Viewed

Total article views: 3,351 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,735 1,501 115 3,351 81 109
  • HTML: 1,735
  • PDF: 1,501
  • XML: 115
  • Total: 3,351
  • BibTeX: 81
  • EndNote: 109
Views and downloads (calculated since 13 Jul 2017)
Cumulative views and downloads (calculated since 13 Jul 2017)

Viewed (geographical distribution)

Total article views: 3,101 (including HTML, PDF, and XML) Thereof 3,097 with geography defined and 4 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Discussed

Latest update: 18 Mar 2024
Download

This preprint has been withdrawn.

Short summary
Peatlands are an important component of the carbon cycle that is expected to change under climate change, but accurate information on the global distribution of peatlands is presently unavailable. We use a machine-learning method to create a map of global peatland extent suitable for use in an Earth system model. For areas where data exists we find excellent agreement with observations and our method has greater skill than solely using soil datasets to estimate peatland coverage.