Coordinate Transformation between Global and Local Datums Based on Artificial Neural Network with K-Fold Cross-Validation: A Case Study, Ghana

Abstract

The popularity of Artificial Neural Network (ANN) methodology has been growing in a wide variety of areas in geodesy and geospatial sciences. Its ability to perform coordinate transformation between different datums has been well documented in literature. In the application of the ANN methods for the coordinate transformation, only the train-test (hold-out cross-validation) approach has usually been used to evaluate their performance. Here, the data set is divided into two disjoint subsets thus, training (model building) and testing (model validation) respectively. However, one major drawback in the hold-out cross-validation procedure is inappropriate data partitioning. Improper split of the data could lead to a high variance and bias in the results generated. Besides, in a sparse dataset situation, the hold-out cross-validation is not suitable. For these reasons, the K-fold cross-validation approach has been recommended. Consequently, this study, for the first time, explored the potential of using K-fold cross-validation method in the performance assessment of radial basis function neural network and Bursa-Wolf model under data-insufficient situation in Ghana geodetic reference network. The statistical analysis of the results revealed that incorrect data partition could lead to a false reportage on the predictive performance of the transformation model. The findings revealed that the RBFNN and Bursa-Wolf model produced a transformation accuracy of 0.229 m and 0.469 m, respectively. It was also realised that a maximum horizontal error of 0.881 m and 2.131 m was given by the RBFNN and Bursa-Wolf. The obtained results per the cadastral surveying and plan production requirement set by the Ghana Survey and Mapping Division are applicable. This study will contribute to the usage of K-fold cross-validation approach in developing countries having the same sparse dataset situation like Ghana as well as in the geodetic sciences where ANN users seldom apply the statistical resampling technique.

Empirical study on the integration of total least squares and radial basis function neural network for coordinate transformation

“…Its efficacy as a coordinate transformation technique is well documented. Literature confirms that the ANN approaches could produce reasonable and promising results that are more satisfactory than the empirical affine, conformal and projective transformation methods (Tierra et al, 2009;Kumi-Boateng and Ziggah, 2017;Ziggah et al, 2016;Ziggah et al, 2019a;Ziggah et al, 2019b;Gullu and Narin, 2019). The strength of the ANN has been credited to its ability to effectively reduce the distortion and heterogeneity in spatial data related to the different geodetic datums.…”

“…Performance criteria indicators (PCIs) such as Horizontal Error (HE), Root Mean Square Horizontal Error (RMSHE), Mean Horizontal Error (MHE), Standard deviation (SD), Maximum Error (Max Error) and Minimum Error (Min Error) were used to check the adequacy of the methods applied. The mathematical representations (Ziggah et al, 2019a) of the various PCIs are given by Equations ( 22) to ( 27).…”

The complementarity and substitutability of sustainable agricultural practices among maize farm households under AFRINT regions in Ghana: Do the socioeconomic determinants confirm these?

“…Ghana is a coastal country in western Africa with latitude and longitude of 8°00ʹN and 2°00ʹW, respectively. It stretches to an area of 239,460 square kilometers (Ziggah et al, 2019) and is rich in natural resources. Ghana has a large proportion of its population that is urban and youthful.…”

A 3D Procrustean Approach to Transform WGS84 Coordinates to Ghana War Office 1926 Reference Datum

“…Survey controls position fixing using satellite based positioning techniques, such as GPS which relies on WGS84 as reference datum, has been on the rise in Ghana over the past two decades. Because the GPS reference datum (WGS84) is globally established, it has become necessary to transform coordinates from the WGS84 into Ghana local geodetic system (War Office 1926) and vice versa (Ayer and Fosu, 2008;Poku-Gyamfi, 2009;Ziggah et al, 2019). This would help to establish a transformation model that can appropriately fits the WGS84 data into Ghana's geodetic geometry for surveying and mapping applications.…”