Global patterns of land‐atmosphere fluxes of carbon dioxide, latent heat, and sensible heat derived from eddy covariance, satellite, and meteorological observations

摘要

We upscaled FLUXNET observations of carbon dioxide, water, and energy fluxes tothe global scale using the machine learning technique, model tree ensembles (MTE). Wetrained MTE to predict site‐level gross primary productivity (GPP), terrestrialecosystem respiration (TER), net ecosystem exchange (NEE), latent energy (LE), andsensible heat (H) based on remote sensing indices, climate and meteorological data, andinformation on land use. We applied the trained MTEs to generate global flux fields at a0.5° × 0.5° spatial resolution and a monthly temporal resolution from 1982 to 2008.Cross‐validation analyses revealed good performance of MTE in predicting among‐siteflux variability with modeling efficiencies (MEf) between 0.64 and 0.84, except for NEE(MEf = 0.32). Performance was also good for predicting seasonal patterns (MEf between0.84 and 0.89, except for NEE (0.64)). By comparison, predictions of monthlyanomalies were not as strong (MEf between 0.29 and 0.52). Improved accounting ofdisturbance and lagged environmental effects, along with improved characterization oferrors in the training data set, would contribute most to further reducing uncertainties. Ourglobal estimates of LE (158 ± 7 J × 1018 yr−1), H (164 ± 15 J × 1018 yr−1), and GPP(119 ± 6 Pg C yr−1) were similar to independent estimates. Our global TER estimate (96 ±6 Pg C yr−1) was likely underestimated by 5–10%. Hot spot regions of interannualvariability in carbon fluxes occurred in semiarid to semihumid regions and were controlledby moisture supply. Overall, GPP was more important to interannual variability in NEEthan TER. Our empirically derived fluxes may be used for calibration and evaluation of landsurface process models and for exploratory and diagnostic assessments of the biosphere.