Towards pairing plot and field scale measurements in managed ecosystems: Using eddy covariance to cross-validate CO 2 fluxes modeled from manual chamber campaigns

•Simultaneous measurements of CO2 fluxes with manual chambers and eddy covariance.•Comparison and cross-validation for two cropping periods (rapeseed, winter wheat).•Different setups for modeling fluxes from chamber campaigns incl. neural networks.•Uncertainty of ±175 g C m−2 on annual net CO2 purely from campaign modeling.•Increased number of campaigns significantly reduced sensitivity to single campaigns.