A multi-ecosystems carbon flux simulation from energy fluxes is presented. A new statistical learning technique based on Artificial Neural Network (ANN) back propagation algorithm and multi-layer perceptron architecture was used in the CO2 simulation. Four input layers (net radiation, soil heat flux, sensible and latent heat flux) were used for training (calibration) and testing (verification) of model outputs. The 15-days half-hourly (grassland) and hourly (forest and cropland) micrometeorological data from eddy covariance observations of AmeriFlux towers were divided into training (5-days) and testing (10-days) sets. Results show that the ANN-based technique predicts CO 2 flux with testing R2 values of 0.86, 0.75 and 0.94 for forest, grassland and cropland ecosystems, respectively. The technique is reliable and efficient to estimate regional or global CO2 fluxes from point measurements and understand the spatiotemporal budget of the CO 2fluxes.
