articleNature CommunicationsSep 11, 2020GOLD OA

Spatial validation reveals poor predictive performance of large-scale ecological mapping models

PPPierre PlotonFMFrédéric MortierMRMaxime Réjou‐MéchainNBNicolas BarbierNPNicolas Picard

Centre National de la Recherche Scientifique · Centre de Coopération Internationale en Recherche Agronomique pour le Développement · +10 more institutions

PubMed
Indexed incrossrefdoajpubmed

Abstract

Mapping aboveground forest biomass is central for assessing the global carbon balance. However, current large-scale maps show strong disparities, despite good validation statistics of their underlying models. Here, we attribute this contradiction to a flaw in the validation methods, which ignore spatial autocorrelation (SAC) in data, leading to overoptimistic assessment of model predictive power. To illustrate this issue, we reproduce the approach of large-scale mapping studies using a massive forest inventory dataset of 11.8 million trees in central Africa to train and validate a random forest model based on multispectral and environmental variables. A standard nonspatial validation method suggests that the…

Citation impact

658
total citations
FWCI
58.03
Percentile
100%
References
61
Citations per year

Authors

13

Topics & keywords

Topics
Keywords
  • Scale (ratio)
  • Spatial ecology
  • Ecology
  • Computer science
  • Environmental science
  • Geography
  • Cartography
  • Biology
UN Sustainable Development Goals
  • Life in Land
No related works found for this paper.

Funding