Assessing the reliability of predicted plant trait distributions at the global scale.

Coline C F Boonman Ana Benítez-López Aafke M Schipper Wilfried Thuiller Madhur Anand Bruno E L Cerabolini Johannes H C Cornelissen Andrés González-Melo Wesley Neil Hattingh Pedro Higuchi Daniel C Laughlin Vladimir G Onipchenko Josep Penuelas Lourens Poorter Nadejda A Soudzilovskaia Mark A J Huijbregts Luca Santini

Published in: Global ecology and biogeography : a journal of macroecology (2020)

Plant community traits can be predicted reliably at the global scale when using an ensemble approach and high-quality data for traits that mostly respond to large-scale environmental factors. We recommend applying ensemble forecasting to account for model uncertainty, using representative trait data, and more routinely assessing the reliability of trait predictions.

Keyphrases

genome wide
electronic health record
dna methylation
big data
convolutional neural network
healthcare
mental health
machine learning
data analysis
artificial intelligence
deep learning