Predicting atmospheric biases for real-time ambiguity resolution in GPS/GLONASS reference station networks

When using multiple reference station networks to support real-time kinematic positioning, the global positioning system (GPS) and/or GLONASS carrier-phase ambiguities associated with between-reference-receiver processing have to be resolved. At the initialisation stage it is not difficult to reliably resolve these ambiguities, in the post-processing mode, using data sets of several hours or days in length. However, due to significant residual atmospheric delays in the double-differenced measurements, it is a big challenge to resolve the ambiguities within the reference station network in real time, particularly in the case of the ambiguities of the newly risen satellites. Both temporal and spatial correlation characteristics for the atmospheric delays are discussed, and appropriate atmospheric delay prediction models are proposed. The experimental results show that the proposed bias prediction models can be used to reliably and efficiently resolve the integer ambiguities within reference station ne tworks in real time, on a single-epoch basis.