Abstract
Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed by Earth System Models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here, we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of peatland formation and include spatially distributed climate, geomorphological and soil data, along with remotely-sensed vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualitative comparisons to other maps in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r2 of 0.73 with a root mean squared error and mean bias error of 9.11 % and −0.36 %, respectively. Our second error estimate was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping products generated through more traditional approaches, at least for boreal peatlands.
Highlights
Peatlands are estimated to cover about three percent of the land surface, but contain approximately one third of the soil carbon, and roughly one tenth of surface freshwater (Joosten and Clarke, 2002; Jackson et al, 2017), and are vulnerable to destabilization due to climate change and anthropogenic pressures including drainage and land use change
As peatlands are commonly considered a type of wetland that contains large amounts of organic carbon in the soil, several 30 studies have set peatland distribution based on maps of soil organic matter density (e.g. Wania et al, 2009; Bechtold et al, 2019; Hugelius et al, 2020)
Using soil organic matter databases alone in determining peatland distribution tends to overlook the vegetation and subsurface hydrology, but most importantly they rely heavily on the fidelity of the soil carbon dataset. Another approach has been to use a soil map together with global wetland maps or inundation extent maps (e.g. Köchy et al, 2015). These wetland and inundated area databases have mostly been produced through mapping of shallow surface 35 water based on remote sensing data, as in the Global Inundation Extent from Multi-Satellites initiative (GIEMS; Prigent et al, 2007; Papa et al, 2010) and the Surface WAter Microwave Product Series (SWAMPS; Schroeder et al, 2015) or land cover mapping using surface observations and moderate resolution imaging spectroradiometer (MODIS) data as in the Global Lake and Wetlands Database (GLWD-3; Lehner and Döll, 2004)
Summary
Peatlands are estimated to cover about three percent of the land surface, but contain approximately one third of the soil carbon, and roughly one tenth of surface freshwater (Joosten and Clarke, 2002; Jackson et al, 2017), and are vulnerable to destabilization due to climate change and anthropogenic pressures including drainage and land use change. The most comprehensive global peatland map we are aware of is PEATMAP (Xu et al, 2018), which was generated through a meta-analysis of regional-scale mapping products of varying spatial resolution and provenance (general land cover maps, soil databases, and a hybrid expert system) This dataset is not well suited as a peatland mask for ESM use as the resolution of some of its parent datasets leaves large polygons of complete peatland cover in regions where this is unlikely and it misses peatlands 50 in regions where peatland coverage is known to exist, e.g. the Russian Republic of Sakha (Yakutia), as it is dependent upon mapping products existing for each region. Following Minasny et al 60 (2019), the peatland covariates useful to DSM can be determined from the drivers of peatland formation, indicators of peat presence, and sensors able to measure the indicators
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
