Potential Natural Vegetation (PNV) is the vegetation cover in equilibrium with climate, that would exist at a given location non-impacted by human activities. PNV is useful for raising public awareness about land degradation and for estimating land potential. Together with the Earth Institute, Columbia University, Woods Hole Research Center, MA USA, School of Archeology, Geography and Environmental Science, University of Reading, UK and Department of Life Sciences and Grantham Institute — Climate Change and the Environment, Imperial College London, UK, we have assessed Machine Learning Algorithms (MLA) for operational mapping of Potential Natural Vegetation (PNV). The following MLA were considered: neural networks (nnet package), random forest (ranger), gradient boosting (gmb), K-nearest neighborhood (class) and cubist. Three case studies were considered: (1) global distribution of biomes based on the BIOME 6000 data set (8057 modern pollen-based site reconstructions), (2) distribution of forest tree species in Europe based on detailed occurrence records (1,546,435 ground observations), and (3) global monthly Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) values (30,301 randomly-sampled points). A stack of 160 global maps representing biophysical conditions over land, including atmospheric, climatic, relief and lithologic variables, were used as explanatory variables. The overall results show that random forest gives the overall best performance. The highest accuracy for predicting BIOME 6000 classes (20) was estimated at 68 % with the most important predictors being total annual precipitation, monthly temperatures and bioclimatic layers. Predicting forest tree species (73) resulted in mapping accuracy of 25%, with the most important predictors being monthly cloud fraction, mean annual and monthly temperatures and elevation. Regression models for FAPAR (monthly images) gave an R-square of 90% with most important predictors being total annual precipitation, monthly cloud fraction, CHELSA bioclimatic layers and month of the year, respectively. Further developments of PNV mapping could include using GBIF records to map global distribution of plant species at different taxonomic levels. This methodology could also be extended to dynamic modeling of PNV, so that future climate scenarios can be incorporated.
Earth Without People?
Maps can be obtained from: http://dx.doi.org/10.7910/DVN/QQHCIK
Github repository with all processing steps: https://github.com/Envirometrix/PNVmaps
Examples of produced maps:
- pnv_biome.type_biome00k_c_1km_s0..0cm_2000..2017_v0.1.tif = Potential Natural Vegetation biomes global predictions of classes (based on the BIOMES 6000 data set)
- pnv_forest.tree.sp_eu.forest00k.fagus.sylvatica_p_1km_s0..0cm_2000..2017_v0.1.tif = Potential Natural Vegetation predicted probability per forest tree species Fagus sylvatica (based on EU forest / GBIF)
- pnv_fapar_proba.v.annual_d_1km_s0..0cm_2014..2017_v0.1.tif = Potential Natural Vegetation FAPAR derived annual mean (based on PROB-V FAPAR)
Please cite as:
- Hengl T, Walsh MG, Sanderman J, Wheeler I, Harrison SP, Prentice IC. (2018) Global mapping of potential natural vegetation: an assessment of Machine Learning algorithms for estimating land potential. PeerJ 6:e5457 https://doi.org/10.7717/peerj.5457
Disclaimer:
To report an issue or artifact in maps, please use https://github.com/envirometrix/PNVmaps/issues.