大气廓线参数反演中基于大气可反演指数的正则化参数选择方法

Selection of regularization parameters using an atmospheric retrievable index in a retrieval of atmospheric profile

以大气可反演指数为指标,采用Nelder-Mead单纯形法求解方法,提出了一种卫星遥感资料反演大气廓线算法中动态的正则化参数选择方案.同时针对四条典型区域廓线,进行了选择试验.从选择结果看,不同廓线所对应的最优正则化参数变化幅度非常小,因此在实际反演过程中,为提高计算效率,可近似取正则化参数为固定值.这为利用卫星遥感资料进行大气廓线反演问题中正则化参数的选择提供了一种可借鉴的方法.

Using an atmospheric retrievable index and The Nelder-Mead simplex method,a dynamic regularization parameter selection method for the retrieval of atmospheric profile with remote sensing data.And a series of test is carried out with four typical regional profiles.The results show that the ranges of the optimal regularization parameter for different profiles are small.And to improve computational efficiency in the actual retrieval process,the regularization parameter can be approximately taken as a constant.The results provide a valuable method of selecting the regularization parameters in the retrieval of atmospheric profiles using the remote sensing data.