全球变化知识资源中心

As a crucial parameter in land surface systems, soil moisture plays an important role in surface energy balance studies, environmental detection, and global climate change research. Remotely sensed data have been used for estimating soil moisture through different approaches, which has resulted in many achievements. Previous studies showed that the land surface temperature (LST) vegetation index method (LST-VI method) can obtain surface soil moisture with remote sensing sources, and it is relatively simple and easy to operate at a regional scale. However, one thorny difficulty is the dry edge determination from the LST-VI feature space. In this study, a remote sensing method is proposed to determine the theoretical dry edge from the LST-VI scatter plots, which do not require any ground measured auxiliary data. Based on the surface energy balance principle, this method derived the maximum LSTs for bare soil and full vegetation cover using MODIS products. The air temperature is parameterized by the LST using a semiempirical formula as the theoretical wet edge. The estimated soil moisture is validated by in situ measurements at a comprehensive weather station of Yucheng. The coefficient of determination is similar to 0.60, and the root mean square error is about 0.08 m(3)/m(3). The relevant key parameters in determining the dry edge are also validated from the meteorological observation. The air temperature and net surface shortwave radiation flux all reach a very high level, with an RMSE of 3.75 k and 49.3 W m(-2), respectively. The results demonstrated that the proposed method can derive the accurate dry edge to estimate soil moisture from the remote sensing data, which will provide great help for future studies of soil moisture estimation using remote sensing techniques. (C) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE)