Application of remote sensing data to extrapolate evapotranspiration (ET) measured at eddy covariance flux towers is a potentially powerful method to estimate continental-scale ET. In support of this concept, we used meteorological and flux data from the AmeriFlux network and an inductive machine learning technique called support vector machine (SVM) to develop a predictive ET model. The model was then applied to the conterminous U.S. In this process, we first trained the SVM to predict 2000-2002 ET measurements from 25 AmeriFlux sites using three remotely sensed variables [land surface temperature, enhanced vegetation index (EVI), and land cover] and one ground-measured variable (surface shortwave radiation). Second, we evaluated the model performance by predicting ET for 19 flux sites in 2003. In this independent evaluation, the SVM predicted ET with a root-mean-square error (rmse) of 0.62 mm/day (approximately 23% of the mean observed values) and an R 2 of 0.75. The rmse from SVM was significantly smaller than that from neural network and multiple-regression approaches in a cross-validation experiment. Among the explanatory variables, EVI was the most important factor. Indeed, removing this variable induced an rmse increase from 0.54 to 0.77 mm/day. Third, with forcings from remote sensing data alone, we used the SVM model to predict the spatial and temporal distributions of ET for the conterminous U.S. for 2004. The SVM model captured the spatial and temporal variations of ET at a continental scale.
The AmeriFlux network of eddy covariance towers has played a critical role in the analysis of terrestrial water and carbon dynamics. It has been used to understand the general principles of ecosystem behaviors and to scale up those principles from sites to regions. To support the generalization from individual sites to large regions, it is essential that all major ecoregions in North America are represented in the AmeriFlux network. In this study, we examined the representativeness of the AmeriFlux network by comparing the climate and vegetation across the coterminous United States in 2004 with those at the AmeriFlux network in 2000–2004 on the basis of remote sensing products. We found that the AmeriFlux network generally captured the climatic and vegetation characteristics in the coterminous United States with under‐representations in the Rocky Mountain evergreen needleleaf forest, the Sierra Nevada Mountains, the Sonora desert, the northern Great Plains, the Great Basin Desert, and New England. In terms of site representativeness, our analysis suggested that Indiana Morgan Monroe State Forest, Indiana, and Harvard Forest, Massachusetts, were among the forest sites with high representativeness extents; while Audubon Research Ranch, Arizona, and Sky Oaks Young Chaparral were among the nonforest sites with high representativeness extents.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.