A hybrid GPS height conversion approach considering of neural network and topographic correction

GPS heights conversion has become a hotspot in survey engineering. With the development of computer and information technology, artificial neural networks (ANN) has been used widely, which has the character of the high parallel distributed processing, associative memory abilities, self organization, self-learning and strong nonlinear mapping abilities, and the theory has proved that one ANN, having deviation and one S-type hidden layer or more plus one linear output layer, could approach any rational function, and the ANN has been used in GPS heights conversion. Topographic correction is to reflect the medium-wave characteristics of the geoid. The paper is focused on the GPS height conversion considering of ANN and topographic correction. The experiments show that the hybrid approach is much validated and something useful is obtained.