Estimation of broadband emissivity (8-12 um) from ASTER data by using RM-NN.

Land surface window emissivity is a key parameter for estimating the longwave radiative budget. The combined radiative transfer model (RM) with neural network (NN) algorithm is utilized to directly estimate the window (8-12 um) emissivity from the brightness temperature of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) with 90 m spatial resolution. Although the estimation accuracy is very high when the broadband emissivity is estimated from AST05 (ASTER Standard Data Product) by using regression method, the accuracy of AST05 is about ± 0.015 for 86 spectra which is determined by the atmosphere correction for ASTER 1B data. The MODTRAN 4 is used to simulate the process of radiance transfer, and the broadband emissivity is directly estimated from the brightness temperature of ASTER 1B data at satellite. The comparison analysis indicates that the RM-NN is more competent to estimate broadband emissivity than other method when the brightness temperatures of band 11, 12, 13, 14 are made as input nodes of dynamic neural network. The estimation average accuracy is about 0.009, and the estimation results are not sensitive to instrument noise. The RM-NN is applied to extract broadband emissivity from an image of ASTER 1B data in China, and the comparison against a classification based multiple bands with 15 m spatial resolution shows that the estimation results from RM-NN are very good.

Estimation of water vapor content in near-infrared bands around 1 mum from MODIS data by using RM-NN.

An algorithm based on the radiance transfer model (RM) and a dynamic learning neural network (NN) for estimating water vapor content from moderate resolution imaging spectrometer (MODIS) 1B data is developed in this paper. The MODTRAN4 is used to simulate the sun-surface-sensor process with different conditions. The dynamic learning neural network is used to estimate water vapor content. Analysis of the simulation data indicates that the mean and standard deviation of estimation error are under 0.06 gcm(-2 )and 0.08 gcm(-2). The comparison analysis indicates that the estimation result by RM-NN is comparable to that of a MODIS water vapor content product (MYD05_L2). Finally, validation with ground measurement data shows that RM-NN can be used to accurately estimate the water vapor content from MODIS 1B data, and the mean and standard deviation of the estimation error are about 0.12 gcm(-2 )and 0.18 gcm(-2).