Premium
Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks
Author(s) -
Papale Dario,
Black T. Andrew,
Carvalhais Nuno,
Cescatti Alessandro,
Chen Jiquan,
Jung Martin,
Kiely Gerard,
Lasslop Gitta,
Mahecha Miguel D.,
Margolis Hank,
Merbold Lutz,
Montagnani Leonardo,
Moors Eddy,
Olesen Jørgen E.,
Reichstein Markus,
Tramontana Gianluca,
Gorsel Eva,
Wohlfahrt Georg,
Ráduly Botond
Publication year - 2015
Publication title -
journal of geophysical research: biogeosciences
Language(s) - English
Resource type - Journals
eISSN - 2169-8961
pISSN - 2169-8953
DOI - 10.1002/2015jg002997
Subject(s) - extrapolation , sampling (signal processing) , artificial neural network , environmental science , eddy covariance , flux (metallurgy) , spatial variability , mathematics , statistics , meteorology , computer science , geography , ecosystem , machine learning , ecology , materials science , filter (signal processing) , metallurgy , computer vision , biology
Empirical modeling approaches are frequently used to upscale local eddy covariance observations of carbon, water, and energy fluxes to regional and global scales. The predictive capacity of such models largely depends on the data used for parameterization and identification of input‐output relationships, while prediction for conditions outside the training domain is generally uncertain. In this work, artificial neural networks (ANNs) were used for the prediction of gross primary production (GPP) and latent heat flux (LE) on local and European scales with the aim to assess the portion of uncertainties in extrapolation due to sample selection. ANNs were found to be a useful tool for GPP and LE prediction, in particular for extrapolation in time (mean absolute error MAE for GPP between 0.53 and 1.56 gC m −2 d −1 ). Extrapolation in space in similar climatic and vegetation conditions also gave good results (GPP MAE 0.7–1.41 gC m −2 d −1 ), while extrapolation in areas with different seasonal cycles and controlling factors (e.g., the tropical regions) showed noticeably higher errors (GPP MAE 0.8–2.09 gC m −2 d −1 ). The distribution and the number of sites used for ANN training had a remarkable effect on prediction uncertainty in both, regional GPP and LE budgets and their interannual variability. Results obtained show that for ANN upscaling for continents with relatively small networks of sites, the error due to the sampling can be large and needs to be considered and quantified. The analysis of the spatial variability of the uncertainty helped to identify the meteorological drivers driving the uncertainty.