Computation of Atmospheric Optical Parameters Based on Deep Neural Network and PCA

The effect of the atmosphere on the propagating energy during the remote sensing imaging simulation is one of the most critical factors affecting the quality of image. The classical methods retrieving atmospheric optical parameters (AOP) have shortcomings in GPU-based imaging simulation application. This paper proposed a method based on deep neural networks (DNN) and principal component analysis (PCA) to compute AOP. Firstly, MODTRAN is employed to obtain large numbers of AOP as original spectrum set in different weather and observation geometry conditions. Then the dimension of original spectrum is reduced by PCA. Next, a DNN is constructed and trained using compressed spectral signatures. Finally, estimated AOP are obtained through inverse PCA by decompressing the output of DNN. The results show that original AOP and estimated AOP have a high spectral similarity which relative error is less than 2%. Compared with the classical methods, DNN can be used to accurately and fast compute AOP with any kind of conditions in remote sensing imaging applications, without consuming large of graphic memory.