Retrieval of Atmospheric and Land Surface Parameters from Satellite-Based Thermal Infrared Hyperspectral Data Using an Artificial Neural Network Technique

摘要

Radiances observed by satellites are influenced by both land surface and atmospheric parameters, and it is difficult to retrieve these parameters simultaneously from multispectral measurements with high accuracies. Even though several methods have been proposed, those methods focus on the retrieval of land surface or atmospheric parameters. Generally, those atmospheric parameters are the atmospheric water vapor and temperature profiles. Thus, this study aims to establish a back propagation artificial neural network (ANN) to retrieve land surface emissivity, land surface temperature (LST), atmospheric transmittance, upward radiance and downward radiance simultaneously from hyperspectral thermal infrared data suitable for various air mass types and surface conditions. The principle component analysis (PCA) technique is first used to compress and remove noise from the data. The evaluation of the ANN using the simulated data indicated that the root mean square error (RMSE) of LST is approximately 0.643 K; the RMSEs of emissivity and transmittance do not exceed 0.011 and 0.016. The RMSEs of upward and downward radiance of all channels are approximately 0.72K and 2.95K, respectively. The results show that the proposed ANN is capable of retrieving atmospheric and land surface parameters with promising accuracies. Because of its simplicity, the proposed ANN can be used to produce preliminary results employed as first estimates for physics-based retrieval method.