Retrieving soil moisture from simulated brightness temperatures by a neural network

Abstract

The authors present the retrievals of surface soil moisture (SM) from simulated brightness temperatures by a newly developed error propagation learning backpropagation (EPLBP) neural network. The frequencies of interest include 6.9 and 10.7 GHz of the advanced microwave scanning radiometer (AMSR) and 1.4 GHz (L-band) of the soil moisture and ocean salinity (SMOS) sensor. The land surface process/radiobrightness (LSP/R) model is used to provide time series of both SM and brightness temperatures at 6.9 and 10.7 GHz for AMSRs viewing angle of 55/spl deg/, and at L-band for SMOS's multiple viewing angles of 0/spl deg/, 10/spl deg/, 20/spl deg/, 30/spl deg/, 40/spl deg/, and 50/spl deg/ for prairie grassland with a column density of 3.7 km/m/sup 2/. These multiple frequencies and viewing angles allow the authors to design a variety of observation modes to examine their sensitivity to SM. For example, L-band brightness temperature at any single look angle is regarded as an L-band one-dimensional (1D) observation mode. Meanwhile, it can be combined with either the observation at the other angles to become an L-band two-dimensional (2D) or a multiple dimensional observation mode, or with the observation at 6.9 or 10.7 GHz to become a multiple frequency/dimensional observation mode. In this paper, it is shown that the sensitivity of radiobrightness at AMSR channels to SM is increased by incorporating L-band radiobrightness. In addition, the advantage of an L-band 2D or a multiple dimensional observation mode over an L-band 1D observation mode is demonstrated.