Uncertainty analysis of CO₂ flux components in subtropical evergreen coniferous plantation

We present an uncertainty analysis of ecological process parameters and CO₂ flux components (R_eco, NEE and gross ecosystem exchange (GEE)) derived from 3 years' continuous eddy covariance measurements of CO₂ fluxes at subtropical evergreen coniferous plantation, Qianyanzhou of ChinaFlux. Daily-differencing approach was used to analyze the random error of CO₂ fluxes measurements and bootstrapping method was used to quantify the uncertainties of three CO₂ flux components. In addition, we evaluated different models and optimization methods in influencing estimation of key parameters and CO₂ flux components. The results show that: (1) Random flux error more closely follows a double-exponential (Laplace), rather than a normal (Gaussian) distribution. (2) Different optimization methods result in different estimates of model parameters. Uncertainties of parameters estimated by the maximum likelihood estimation (MLE) are lower than those derived from ordinary least square method (OLS). (3) The differences between simulated R_eco, NEE and GEE derived from MLE and those derived from OLS are 12.18% (176 g C · m^-2 · a^-1), 34.33% (79 g C · m^-2 · a^-1) and 5.4% (92 g C · m^-2 · a^-1). However, for a given parameter optimization method, a temperature-dependent model (T_model) and the models derived from a temperature and water-dependent model (TW_model) are 1.31% (17.8 g C · m^-2 · a^-1), 2.1% (5.7 g C · m^-2 · a^-1), and 0.26% (4.3 g C · m^-2 · a^-1), respectively, which suggested that the optimization methods are more important than the ecological models in influencing uncertainty in estimated carbon fluxes. (4) The relative uncertainty of CO₂ flux derived from OLS is higher than that from MLE, and the uncertainty is related to timescale, that is, the larger the timescale, the smaller the uncertainty. The relative uncertainties of R_eco, NEE and GEE are 4%-8%, 7%-22% and 2%-4% respectively at annual timescale.