A map of global peatland extent created using machine learning (Peat-ML)

Joe R. Melton, Ed Chan, Koreen Millard, Matthew Fortier, R. Scott Winton, Javier M. Martín-López, Hinsby Cadillo‐Quiroz, Darren Kidd, Louis VerchotZenodo 2021 · DOI · OpenAlex

Abstract

Map of global peatland extent estimated by machine learning. The download includes both a netcdf file version and a GeoTIFF (as a zip archive) Abstract from associated paper: Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and<br> hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed<br> by Earth System Models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here,<br> we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning<br> techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of<br> peatland formation and include spatially distributed climate, geomorphological and soil data, along with remotely-sensed<br> vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with<br> mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualititative comparisons to other maps<br> in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out<br> cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r<sup>2</sup><br> of 0.73 with a root mean squared error and mean bias error of 9.11% and -0.36%, respectively. Our second error estimate<br> was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited<br> Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping<br> products generated through more traditional approaches, at least for boreal peatlands.
BibTeX
@inproceedings{melton2021map,
  author = {Joe R. Melton and Ed Chan and Koreen Millard and Matthew Fortier and R. Scott Winton and Javier M. Martín-López and Hinsby Cadillo‐Quiroz and Darren Kidd and Louis Verchot},
  title = {{A map of global peatland extent created using machine learning (Peat-ML)}},
  booktitle = {Zenodo},
  year = {2021},
  doi = {10.5281/zenodo.5794335},
}

Loading related content...

Figure