Partitioning evapotranspiration with concurrent eddy covariance measurements in a mixed forest

Plants have an important effect on our climate: as they assimilate atmospheric CO2 through the process of photosynthesis, they also transpire water to the atmosphere and thereby influence surface temperatures. It is, however, difficult to quantify transpiration from ecosystems due to measurement limitations. Direct eddy covariance (EC) measurements are currently the best available approach to observe interactions linked to biosphere-atmosphere CO2 and water vapor exchange. While there are well-established methods to partition CO2 fluxes into the component fluxes of photosynthesis and respiration, there is still no standardized method to partition water vapor fluxes (evapotranspiration, ET) into the component fluxes of evaporation and transpiration. In this study, we used two years of concurrent below and above canopy EC measurements in a mixed deciduous forest in Switzerland to partition water vapor fluxes into the components of transpiration (biological) and evaporation (physical). We compare our results with transpiration from the ecosystem demographic (ED2) model as well as derived from plot-level sap flow measurements. EC-derived transpiration accounted on average for 74% of ET, emphasizing a considerably lower contribution from evaporation. EC and sap flow measurements showed mid-afternoon reductions in transpiration during periods of high vapor pressure deficit in summer. Reductions in ET and transpiration were found under limiting soil moisture conditions, while the ratio of transpiration to ET remained constant over the years due to the low and rather constant evaporation in this closed canopy forest. Stomatal regulation in response to enhanced atmospheric evaporative demand was also found under water-stressed conditions in the afternoon in summer. When comparing our EC-derived evaporation with the ED2 model, we found large discrepancies linked to the challenge of modeling evaporation in a light limited, yet variable environment below the canopy. A strong correlation was found for transpiration from ED2 with the EC-based estimates. Our results show the potential of concurrent below and above canopy EC measurements to partition ecosystem ET in forests.