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

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.

[1]  G. Veis.  Geodetic Uses of Artificial Satellites , 1960 .

[2]  K. V. Prema,et al.  Generalization Capability of Artificial Neural Network Incorporated with Pruning Method , 2011, ADCONS.

[3]  Yao Yevenyo Ziggah,et al.  Accuracy Assessment of Cartesian (X, Y, Z) to Geodetic Coordinates (φ, λ, h) Transformation Procedures in Precise 3D Coordinate Transformation – A Case Study of Ghana Geodetic Reference Network , 2016 .

[4]  Will Featherstone,et al.  An updated explanation of the geocentric datum of Australia (GDA) and its effects upon future mapping , 1996 .

[5]  Yao Yevenyo Ziggah,et al.  Performance evaluation of artificial neural networks for planimetric coordinate transformation—a case study, Ghana , 2016, Arabian Journal of Geosciences.

[6]  A. R. Tierra,et al.  Using an Artificial Neural Network to Transformation of Coordinates from PSAD56 to SIRGAS95 , 2009 .

[7]  Y. Y. Ziggah,et al.  ACCURACY ASSESSMENT OF CENTROID COMPUTATION METHODS IN PRECISE GPS COORDINATES TRANSFORMATION PARAMETERS DETERMINATION - A CASE STUDY, GHANA , 2013 .

[8]  Yuanxi Yang,et al.  Chinese geodetic coordinate system 2000 , 2009 .

[9]  Determination of GPS Coordinate Transformation Parameters of Geodetic Data between Reference Datums-A Case , 2013 .

[10]  Ertan Gökalp,et al.  A Study on 2D similarity transformation using multilayer perceptron neural networks and a performance comparison with c onventional and robust outlier detection methods , 2016 .

[11]  Tomislav Bašić,et al.  Empirical comparison of the Geodetic Coordinate Transformation Models: a case study of Croatia , 2017 .

[12]  Yao Yevenyo Ziggah,et al.  NOVEL APPROACH TO IMPROVE GEOCENTRIC TRANSLATION MODEL PERFORMANCE USING ARTIFICIAL NEURAL NETWORK TECHNOLOGY , 2017 .

[13]  Bernard Kumi-Boateng,et al.  Ramification of Datum and Ellipsoidal Parameters on Post Processed Differential Global Positioning System (DGPS) Data - A Case Study* , 2015 .

[14]  Mevlut Gullu.  Coordinate transformation by radial basis function neural network , 2010 .

[15]  Helmut K. Wolf.  Geometric connection and re-orientation of three-dimensional triangulation nets , 1963 .

[16]  Hybridized centroid technique for 3D Molodensky-Badekas coordinate transformation in the Ghana geodetic reference network using total least squares approach , 2016 .

[17]  B. R. Bowring,et al.  TRANSFORMATION FROM SPATIAL TO GEOGRAPHICAL COORDINATES , 1976 .

[18]  Piroska Zaletnyik.  COORDINATE TRANSFORMATION WITH NEURAL NETWORKS AND WITH POLYNOMIALS IN HUNGARY Ms , 2005 .

[19]  P. Burman.  A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods , 1989 .

[20]  H. Hemond,et al.  Extended artificial neural networks: incorporation of a priori chemical knowledge enables use of ion selective electrodes for in-situ measurement of ions at environmentally relevant levels. , 2013, Talanta.

[21]  Charles D. Ghilani,et al.  Adjustment Computations: Spatial Data Analysis , 2006 .

[22]  Anthony Baabereyir.  Urban environmental problems in Ghana: a case study of social and environmental injustice in solid waste management in Accra and Sekondi-Takoradi , 2009 .

[23]  I. Yilmaz,et al.  Georeferencing of historical maps using back propagation artificial neural network , 2012, Experimental Techniques.

[24]  Alfonso Tierra,et al.  Planes coordinates transformation between PSAD56 to SIRGAS using a Multilayer Artificial Neural Network , 2014 .

[25]  Cutberto Uriel Paredes-Hernández,et al.  HORIZONTAL POSITIONAL ACCURACY OF GOOGLE EARTH’S IMAGERY OVER RURAL AREAS: A STUDY CASE IN TAMAULIPAS, MEXICO , 2013 .

[26]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[27]  Bayram Turgut,et al.  A back-propagation artificial neural network approach for three-dimensional coordinate transformation , 2010 .

[28]  J. Ayer,et al.  Map Coordinate Referencing and the Use of GPS Datasets in Ghana , 2008 .

[29]  A. Tierra,et al.  Using an artificial neural network to improve the transformation of coordinates between classical geodetic reference frames , 2008, Comput. Geosci..

[30]  Xu Peiliang,et al.  Overview of Total Least Squares Methods , 2013 .

[31]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[32]  John Badekas,et al.  INVESTIGATION RELATED TO THE ESTABLISHMENT OF A WORLD GEODETIC SYSTEM. , 1969 .

[33]  Z. Reitermanová.  Data Splitting , 2010 .

[34]  Lao-Sheng Lin.  A STUDY ON CADASTRAL COORDINATE TRANSFORMATION USING ARTIFICIAL NEURAL NETWORK , 2006 .

[35]  Ertan Gökalp,et al.  2D COORDINATE TRANSFORMATION USING ARTIFICIAL NEURAL NETWORKS , 2016 .

[36]  Sri Niwas Singh,et al.  Fast static available transfer capability determination using radial basis function neural network , 2011, Appl. Soft Comput..

[37]  Heping Pan,et al.  Capability of self-organizing map neural network in geophysical log data classification: Case study from the CCSD-MH , 2015 .

[38]  Yoonsuh Jung,et al.  A K-fold averaging cross-validation procedure , 2015, Journal of nonparametric statistics.

[39]  Yoshua Bengio,et al.  No Unbiased Estimator of the Variance of K-Fold Cross-Validation , 2003, J. Mach. Learn. Res..

[40]  Gene H. Golub,et al.  Singular value decomposition and least squares solutions , 1970, Milestones in Matrix Computation.

[41]  Laverle Berry.  Ghana: A Country Study , 1995 .

[42]  Sabine Van Huffel,et al.  Total least squares problem - computational aspects and analysis , 1991, Frontiers in applied mathematics.

[43]  Richard Fiifi Annan,et al.  Determination of 3D Transformation Parameters for the Ghana Geodetic Reference Network using Ordinary Least Squares and Total Least Squares Techniques , 2017 .

[44]  M. I. Yurkina,et al.  Methods for study of the external gravitational field and figure of the earth , 1962 .

[45]  Constantin-Octavian Andrei,et al.  3D affine coordinate transformations , 2006 .

[46]  Mustafa Yilmaz,et al.  Datum Transformation by Artificial Neural Networks for Geographic Information Systems Applications , 2012 .