摘要：Accurate modeling of thermospheric mass density variation is of foremost importance to low Earth orbital prediction. The accuracy of empirical neutral density models based on global indices for solar and geomagnetic activity is inherently limited by the resolution of these indices. Assimilative modeling is appealing, as it provides a means to systematically identify and correct the inconsistencies between model specification and observations. In this paper we present a practical assimilative mass density specification methodology that optimally combines the mass density prediction by the Coupled-Thermosphere-Ionosphere-Plasmasphere-electrodynamics (CTIPe) model with in-situ observations of neutral mass density by research satellites such as Challenging Minisatellite Payload (CHAMP) and Gravity Recovery and Climate Experiment (GRACE). The methodology yields an analysis of the global density according to Bayes's rule under the assumption of Gaussian prior and observation error distribution (namely, by using the Optimal Interpolation or Kalman Filter update formula). To make best use of under-sampled global neutral mass density observations, the background (prior) error covariance is built on the principal component analysis to represent the long-distance correlation effectively, with an adaptive capability by using the maximum-likelihood method. The neutral mass density specification at 400 km can be improved up to 50% beyond what has been attained by the CTIPe by assimilating CHAMP and GRACE density observations.
