Effects of Spatial Resolution for Evapotranspiration Estimation by Using the Triangular Method Over Heterogeneous Underling Surface

Abstract

In order to verify the applicability of different triangular methods for evapotranspiration (ET) estimation and the effect of spatial resolution on triangular methods, the applicability of normalized-difference vegetation index-land surface temperature (NDVI-LST) and NDVI-albedo triangular methods was validated based on the enhanced thematic mapper (ETM)+ moderate-resolution imaging spectrometer (MODIS) data. Considering the effecting of soil moisture on ET, a new triangular method was developed by using the perpendicular drought index (PDI). Compared to the measured values, the result showed that LSTs retrieved by a single-channel method using ETM+ data were closed to the measured values, with a root-mean-square error (RMSE) of 5.7 K. Given the inhomogeneity of the underlying surface, the remote-sensing data related to the low spatial resolution blur the between-pixel differences. A higher spatial resolution of the remote sensing (RS) data corresponds to a greater homogeneity of the distribution of scatter plots in the eigenspace and greater differences between pixels, particularly in the NDVI-LST eigenspace. The eigenspace formed by the PDI and the NDVI possess distinct triangular characteristics, particularly the inversion results of the ETM+ data, with an mean absolute percent error of 14% and an RMSE of 103 W·m−2 . The dry-edge slope introduced by the PDI in the expression increases the accuracy of the estimated ET. Compared to the measured data, the RMSEs of ET estimated by the NDVI-PDI using the ETM+ and MODIS data were reduced to 92 and 121 W⋅m−2, respectively. The regional distribution of ET inverted by the NDVI-PDI method significantly coincided with the actual scenario of the underlying surface.