Estimating surface heat and water vapor fluxes by combining two-source energy balance model and back-propagation neural network

Abstract

The accurate quantification of surface heat and water vapor fluxes is significantly essential for understanding water balance dynamics. In this study, 15-m spatial resolution turbulent fluxes (H and LE) in the Zhangye oasis situated the middle reaches of the Heihe River Basin (HRB) were estimated by the remote sensing-based two-source energy balance model (TSEB). The TSEB model uses temperature including land surface temperature (LST) and air temperature (Ta) as the main input variable to compute turbulent fluxes but their spatial resolution is rather limited. To overcome this shortcoming, the 15-m spatial resolution LST and Ta were obtained by using the back-propagation neural network (BPNN). The results indicated that the BPNN was able to obtain finer spatial resolution and LST and Ta; the root mean square error (RMSE) values of LST and Ta are 1.99 K and 0.50 K, respectively. The remotely sensed H and LE predicted by TSEB model utilizing the LST and Ta modeled by BPNN. The results showed that H and LE agreed well with the flux observations from multi-set eddy covariance (EC) systems installed at a number of sites and covering all representative land cover types; particularly for the latent heat flux, its estimates produced mean absolute percent errors (MAPE) of 8.76% for maize, 20.17% for vegetable, 29.06% for residential area, and 16.12% for orchard. This study obtained surface heat and water vapor fluxes at finer spatial resolution than the other flux estimates from the remote sensing models that have been used in the Zhangye oasis. The results produced by combining the TSEB model and BPNN can provide more information for drafting reliable sustainable water resource management schemes and improving the irrigation water use efficiency in arid and semi-arid regions.