气候变化领域集成服务门户

Photosynthesis (gross primary production, GPP) and evapotranspiration (ET) are ecosystem processes with global significance for climate, the global carbon and hydrological cycles and a range of ecosystem services. The mechanisms governing these processes are complex but well understood. There is strong coupling between these processes, mediated directly by stomatal conductance and indirectly by root zone soil moisture content and its accessibility. This coupling must be effectively modelled for robust predictions of earth system responses to global change. Yet, it is highly demanding to model leaf and cellular processes, like stomatal conductance or electron transport, with response times of minutes, over decadal and global domains. Computational demand means models resolving this level of complexity cannot be easily evaluated for their parameter sensitivity nor calibrated using earth observation information through data assimilation approaches requiring large ensembles. To overcome these challenges, here we describe a coupled photosynthesis evapotranspiration model of intermediate complexity. The model reduces computational load and parameter numbers by operating at canopy scale and daily time step. Through the inclusion of simplified representation of key process interactions, it retains sensitivity to variation in climate, leaf traits, soil states and atmospheric CO2. The new model is calibrated to match the biophysical responses of a complex terrestrial ecosystem model (TEM) of GPP and ET through a Bayesian model-data fusion framework. The calibrated ACM-GPP-ET generates unbiased estimates of TEM GPP and ET and captures 80 %-95% of the sensitivity of carbon and water fluxes by the complex TEM. The ACM-GPPET model operates 3 orders faster than the complex TEM. Independent evaluation of ACM-GPP-ET at FLUXNET sites, using a single global parameterisation, shows good agreement, with typical R-2 similar to 0.60 for both GPP and ET. This intermediate complexity modelling approach allows full Monte Carlo-based quantification of model parameter and structural uncertainties and global-scale sensitivity analyses for these processes and is fast enough for use within terrestrial ecosystem model-data fusion frameworks requiring large ensembles.