摘要：There has been a need for geodetic network densification since the early days of traditional surveying. In order to densify geodetic networks in a way that will produce the most effective reference frame improvements, the crustal velocity field must be modelled. Artificial Neural Networks (ANNs) are widely used as function approximators in diverse fields of geoinformatics including velocity field determination. Deciding the number of hidden neurons required for the implementation of an arbitrary function is one of the major problems of ANN that still deserves further exploration. Generally, the number of hidden neurons is decided on the basis of experience. This paper attempts to quantify the significance of pruning away hidden neurons in ANN architecture for velocity field determination. An initial back propagation artificial neural network (BPANN) with 30 hidden neurons is educated by training data and resultant BPANN is applied on test and validation data. The number of hidden neurons is subsequently decreased, in pairs from 30 to 2, to achieve the best predicting model. These pruned BPANNs are retrained and applied on the test and validation data. Some existing methods for selecting the number of hidden neurons are also used. The results are evaluated in terms of the root mean square error (RMSE) over a study area for optimizing the number of hidden neurons in estimating densification point velocity by BPANN.
