Speaker
Description
Computational intelligent algorithms have emerged as new paradigm shift in geosciences computations and applications. The present study aims to perform coordinate transformation using a novel technique called the group method of data handling (GMDH). The data used for the coordinate transformation constitute the Ghana national triangulation network which is based on the two horizontal geodetic datums (Accra 1929 and Leigon 1977) utilised for geospatial applications in Ghana. The obtained GMDH model result was compared with other investigative methods such as backpropagation neural network (BPNN), radial basis function neural network (RBFNN), multivariate adaptive regression spline (MARS), 2D conformal, and 2D affine model. It was noticed that the proposed GMDH model is very efficient in transforming coordinates from the Leigon 1977 datum to the official mapping datum of Ghana, i.e. Accra 1929 datum. It was also found that GMDH could produce comparable results with the widely used BPNN, RBFNN and MARS. The classical transformation methods (2D affine and 2D conformal) performed poorly in comparison with the intelligent systems. The application of the GMDH will serve as a supplement to transformation procedures in the Ghana geodetic reference network. The proposed GMDH approach could also be used in developing countries yet to establish geocentric datum and have the same geodetic network infrastructure like Ghana.
