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

Abstract

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.

Fires prime terrestrial organic carbon for riverine export to the global oceans

“…For example, we identified a linear relationship between peatland extent and the DBC content of DOC in the 6 major high-latitude rivers included in our global data set (R 2 = 0.68, p < 0.05; Supplementary Fig. 1) 57 . We suggest that this relationship occurs because the DOC in channels draining peatlands is enriched in DBC (14.8 ± 2.3%) relative to channels draining boreal forest (5.4 ± 1.1%) and glaciers (2.1 ± 1.0%) ( Fig.…”

Modelling northern peatland area and carbon dynamics since the Holocene with the ORCHIDEE-PEAT land surface model (SVN r5488)

“…Area Simulated peatland area in 2009 is evaluated against the (1) World Inventory of Soil Emission potentials (WISE) database (Batjes, 2016); (2) an improved global peatland map (PEATMAP) by reviewing a wide variety of global-, regional-, and local-scale peatland distribution information (Xu et al, 2018); (3) International Mire Conservation Group Global Peatland Database (IMCG GPD) (Joosten, 2010); and the (4) peatland distribution map by Yu et al (2010).…”

“…Some studies prescribe peatlands from wetlands. However, in spite of the fact that there are extensive disagreements between wetland maps, it is a challenge to distinguish peatlands from non-peat-forming wetlands (Gumbricht et al, 2017;Kleinen et al, 2012;Melton et al, 2013;Xu et al, 2018). Estimates based on peatland inventories are impeded by poor availability of data, nonuniform definitions of peatlands among regions, and coarse resolution (Joosten, 2010;Yu et al, 2010).…”

Development of a global dataset of Wetland Area and Dynamics for Methane Modeling (WAD2M)

“…However, the spatial resolution of WAD2M is dictated by the resolution of its input data on wetland dynamic dataset unless a downscaling methodology is applied. Downscaling can also be used to improve spatial resolution using artificial neural networks (see https://hess.copernicus.org/articles/22/5341/2018/hess-22-5341-2018discussion.html) Machine learning approaches (Alemohammad et al, 2018;Kratzert et al, 2018;Wu et al, 2017) or physically-based hydrological models (Gumbricht, 2018), together with higher resolution images (e.g. Landsat, ALOS 1&2) are better suited to capture inundation features at fine scales.…”