Water and carbon fluxes above European coniferous forests modelled with artificial neural networks

Artificial neural networks are used to select a minimal set of input variables to model water vapour and carbon exchange of coniferous forest ecosystems, independently of tree species and without detailed physiological information. Neural networks are used because of their power to fit highly non-linear relations between input and output-variables. Radiation, temperature, vapour pressure deficit and time of the day showed to be the dynamic input variables that determine ecosystem water fluxes. The same variables, together with projected leaf area index are needed for modelling CO₂-fluxes. The results for the individual sites show that the neural networks found mean water and carbon flux responses to the driving variables valid for all sites. The sensitivity analysis of the derived neural networks shows that the LAI-effect of the CO₂-flux model is overfitted because of the low variability of LAI. However, the predictions of CO₂-fluxes of sites not included in the calibration set indicate that the LAI-response of the network is reliable and that results can be used as a first estimate of the net ecosystem carbon exchange of the forest sites. Independent predictions of forest ecosystem vapour fluxes were equally satisfying as empirical models specifically calibrated for the individual sites. The results indicate that both short term water and carbon fluxes of European coniferous forests can be modelled without using detailed physiological and site specific information.