The goal of this study is to scale aircraft measured fluxes of sensible and latent heat to the North Slope of Alaska and develop high resolution flux maps. For this purpose we analyzed an eddy-covariance data set obtained by the research aircraft POLAR 5 as part of the AIRMETH-2012 campaign, and investigated the spatial patterning of energy fluxes. Environmental response functions between flux observations and corresponding biophysical and meteorological drivers were estimated using a combination of time-frequency decomposition, dispersion modeling and machine learning. The extracted relationships are then used to scale observational data across heterogeneous Arctic landscapes, thus improving the spatial coverage and representativeness of the energy fluxes. Maps of projected energy fluxes are used to asses energy partitioning in northern ecosystems and to determine dominant energy exchange processes of permafrost area.