Abstract
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.
Highlights
There has been a need for geodetic network densification since the early days of traditional surveying
The main objective of this study is to evaluate back propagation artificial neural network (BPANN) with different number of hidden neurons for optimizing the architecture of BPANN in estimating the velocities of Global Positioning System (GPS) densification points
The analysis of the root mean square error (RMSE) values given in Appendix, Figure 3 reveals that the training data set, the testing data set and the validation data set are very similar
Summary
There has been a need for geodetic network densification since the early days of traditional surveying. The general objective of network densification is to provide a more convenient accurate access to the reference frame (FERLAND et al, 2002). The densification of the geodetic networks is necessary in support of large-scale mapping applications, cadastral measurement and geodetic point construction. The Global Positioning System (GPS) is most frequently used to densify geodetic networks. Densifying the geodetic networks in Turkey require determining the positions of potential new GPS sites with reference to the locations of existing GPS sites (TURKISH CHAMBER OF SURVEY AND CADASTRE ENGINEERS, 2008). It is necessary to estimate the velocity vectors of the densification points in order to obtain the associated coordinates with the reference GPS epoch
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have