Application of Multivariate Adaptive Regression Spline (MARS) Approach for 2D Coordinate Transformation

Yao Yevenyo Ziggah, Prosper Basommi Laari

Abstract


Coordinate transformation is still an on-going research area in the geodetic sciences. It allow coordinates to be transformed from a source datum onto a target datum and vice versa for practical geodetic applications. Multivariate Adaptive Regression Spline (MARS) is a machine learning technique that has been successfully applied to solve function estimation problems in several disciplines. However, its application in geodetic sciences for coordinate transformation is yet to be explored. In this study, an attempt has been made to explore the performance of MARS as a novel alternative technique for coordinate transformation. The MARS was applied in this study to transform two-dimensional (2D) coordinates between the two national geodetic datums (Accra 1929 and Leigon 1977) used in Ghana. The results were further analysed and compared with Backpropagation Neural Network (BPNN) and Radial Basis Function Neural Network (RBFNN) as well as two classical transformation methods namely, 2D conformal and 2D affine models, respectively. The analyses were based on the horizontal positional residuals obtained between the observed and estimated horizontal coordinates. The statistical findings revealed that a maximum horizontal positional error of 0.628, 0.509 and 1.624 m were respectively produced by the MARS, RBFNN and BPNN. While, 2.153 and 2.642 m were correspondingly given by 2D affine and 2D conformal models. In addition, a minimum horizontal positional error of 0.017, 0.005 and 0.040 m were obtained by the MARS, RBFNN and BPNN. In contrast, the 2D affine and 2D conformal models had 0.109 and 0.199 m, respectively. Furthermore, in terms of the precision of the estimated horizontal coordinates, the MARS obtained a standard deviation of 0.139 m while 0.119 and 0.273 m were achieved correspondingly by RBFNN and BPNN. The 2D affine and 2D conformal produced 0.468 and 0.510 m. It was therefore concluded that the proposed MARS can be a promising technique for coordinate transformation in the Ghana geodetic reference network.

Keywords


Multivariate Adaptive Regression Spline; Radial Basis Function Neural Network; Backpropagation Neural Network; Coordinate Transformation

Full Text:

PDF

References


Annan, R. F., Ziggah, Y. Y., Ayer, J. and Odutola, C.A. (2016), “A Hybridized Centroid Technique for 3D Molodensky-Badekas Coordinate Transformation in the Ghana Geodetic Reference Network using Total Least Squares Approach”, South African Journal of Geomatics, Vol. 5, No. 3, pp. 269-284.

Amoussou-Coffi, A., Yu-Yong, J., Li, W., Hao, W. and Zi-Hao, W. (2013), “Predicting Tunnel Convergence using Multivariate Adaptive Regression Spline and Artificial Neural Network”, Tunnelling and Underground Space Technology, Vol. 38, pp. 368-376.

Applebaum, L. T. (1982), “Geodetic Datum Transformation by Multiple Regression Equations”, Third International Geodetic Symposium on Satellite Doppler Positioning, New Mexico State University, Las Cruces, New Mexico, pp. 207-223.

Ayer, J. (2008), “Transformation Models and Procedures for Framework Integration of the Ghana National Geodetic Network”, The Ghana Surveyor, Vol. 1, No. 2, pp. 52-58.

Ayer, J. and Fosu, C. (2008), “Map Coordinates Referencing and the use of GPS Datasets in Ghana”, Journal of Science and Technology, Vol. 28, No. 1, pp. 116-127.

Ayer, J. and Tiennah, T. (2008), “Datum Transformations by Iterative Solution of the Abridging Inverse Molodensky Formulae”, The Ghana Surveyor, Vol. 1, No. 2, pp. 59-66.

Badekas, J. (1969), “Investigations Related to the Establishment of a World Geodetic System”, Technical Report, The Ohio State University, Department of Geodetic Science, Columbus, Ohio State, USA, No. 124, 181 pp.

Bishop, C. M. (1995), Neural networks for pattern recognition, Oxford University Press, Oxford, UK, 482 pp.

Bursa, M. (1962), “The Theory of the Determination of the Nonparallelism of the Minor Axis of the Reference Ellipsoid, Polar axis of the Earth, and Initial Astronomical and Geodetic Meridians from Observation of Artificial Earth Satellites”, Studia Geophysica et Geodaetica, Vol. 6, No. 2, pp. 209-214.

Constantin-Octavian, A. (2006), “3D Affine Coordinate Transformations”, Master of Science Thesis, School of Architecture and the Built Environment, Royal Institute of Technology (KTH), Sweden, pp. 1-40.

Durmaz, M., Karslioglu, M.O. and Nohutcu, M. (2010), “Regional VTEC Modeling with Multivariate Adaptive Regression Splines”, Advances in Space Research, Vol. 46, No. 2, pp. 180-189.

Dzidefo, A. (2011), “Determination of Transformation Parameters Between the World Geodetic System 1984 and the Ghana Geodetic Network”, Master’s Thesis, Department of Civil and Geomatic Engineering, KNUST, Kumasi, Ghana, pp. 1-97.

ElSayed, M. S. and Ali, A. H. (2016), “Performance Evaluation of Applying Fuzzy Multiple Regression Model to TLS in the Geodetic Coordinate Transformation”, American Scientific Research Journal for Engineering, Technology, and Sciences, Vol. 25, No. 1, pp. 36-50.

Friedman, J.H. (1991), “Multivariate Adaptive Regression Splines”, The Annals of Statistics, Vol. 19, No. 1, pp. 1-141.

Fu, B. and Liu, X. (2014), “Application of Artificial Neural Network in GPS Height Transformation”, In Applied Mechanics and Materials, Vol. 501, pp. 2162-2165.

Gao, C. Y., Cui, X. M. and Hong, X. Q. (2014), “Study on the Applications of Neural Networks for Processing Deformation Monitoring Data”, In Applied Mechanics and Materials, Vol. 501, pp. 2149-2153.

Ghilani, C.D. (2010), Adjustment Computations: Spatial Data Analysis, 5th edition, John Wiley & Sons Inc., Hoboken, New Jersey, 672 pp.

Gil, J. and Mrowczynska, M. (2012), “Methods of Artificial Intelligence used for Transforming a System of Coordinates”, Geodetski List, Vol. 66, No. 4, pp. 321-336.

Gullu, M. (2010), “Coordinate Transformation by Radial Basis Function Neural Network”, Scientific Research and Essays, Vol. 5, No. 20, pp. 3141-3146.

Gullu, M., Yilmaz, M., Yilmaz, I. and Turgut, B. (2011), “Datum Transformation by Artificial Neural Networks for Geographic Information Systems Applications”, In International Symposium on Environmental Protection and Planning: Geographic Information Systems (GIS) and Remote Sensing (RS) Applications (ISEPP), Izmir, Turkey, pp. 13-19.

Hajian, A., Ardestani, E.V. and Lucas, C. (2011), “Depth Estimation of Gravity Anomalies using Hopfield Neural Networks”, Journal of the Earth & Space Physics, Vol. 37, No. 2, pp. 1-9.

Hamid, R. S. and Mohammad, R.S. (2013), “Neural Network and Least Squares Method (ANN-LS) for Depth Estimation of Subsurface Cavities Case Studies: Gardaneh Rokh Tunnel, Iran”, Journal of Applied Science and Agriculture, Vol. 8, No. 3, pp. 164-171.

Haykin, S. (1990), Neural networks: A Comprehensive Foundation, 2nd Edition, Prentice-Hall, New Jersey, 842 pp.

Hornik, K., Stinchcombe, M. and White, H. (1989), “Multilayer Feed Forward Networks are Universal Approximators”, Neural Networks, Vol. 2, No. 5, pp. 359-366.

Kavzoglu, T. and Saka, M. H. (2005), “Modelling Local GPS/Levelling Geoid Undulations Using Artificial Neural Networks”, Journal of Geodesy, Vol. 78, No. 9, pp. 520–527.

Konakoğlu, B. and Gökalp, E. (2016), “A Study on 2D Similarity Transformation Using Multilayer Perceptron Neural Networks and a Performance Comparison with Conventional and Robust Outlier Detection Methods”, Acta Montanistica Slovaca, Vol. 21, No. 4, pp. 324-332.

Konakoğlu, B., Cakir, L. and Gökalp, E. (2016). “2D Coordinates Transformation Using Artificial Neural Networks”, International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, Istanbul, Turkey, pp. 183-186.

Kumi-Boateng, B. and Ziggah, Y. Y. (2016), “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”, Journal of Geosciences and Geomatics, Vol. 4, No. 1, pp. 1-7.

Kumi-Boateng, B. and Ziggah, Y. Y. (2017), “Horizontal Coordinate Transformation Using Artificial Neural Network Technology- A Case Study of Ghana Geodetic Reference Network”, Journal of Geomatics, Vol. 11, No. 1, pp. 1-11.

Laari, P. B., Ziggah, Y. Y. and Annan, R. F (2016), “Determination of 3D Transformation Parameters for the Ghana Geodetic Reference Network using Ordinary Least Squares and Total Least Squares Techniques”, International Journal of Geomatics and Geosciences, Vol. 7, No. 3, pp. 245-261.

Lao-Sheng, L. and Yi-Jin, W. (2006), “A Study on Cadastral Coordinate Transformation Using Artificial Neural Network”, Proceedings of the 27th Asian Conference on Remote Sensing, Ulaanbaatar, Mongolia, pp. 1-6.

Lei, W. and Qi, X. (2010), “The Application of BP Neural Network in GPS Elevation Fitting”, International Conference on Intelligent Computation Technology and Automation, Changsha-China, IEEE, Vol. 3, pp. 698-701.

Li, X., Zhou, J. and Guo, R. (2014), “High-Precision Orbit Prediction and Error Control Techniques for COMPASS Navigation Satellite”, Chinese Scientific Bulletin, Vol. 59, No. 23, pp. 2841-2849.

Liao, D. C, Wang, Q. J, Zhou, Y. H., Liao, X. H and Huang, C. L. (2012), “Longterm Prediction of the Earth Orientation Parameters by the Artificial Neural Network Technique”, Journal of Geodynamics, Vol. 62, pp. 87-92.

Manzano-Agugliaro, F., San-Antonio-Gómez, C., López, S., Montoya, F.G. and Gil, C. (2013), “Pareto-Based Evolutionary Algorithms for the Calculation of Transformation Parameters and Accuracy Assessment of Historical Maps”, Computers and Geosciences, Vol. 57, pp. 124-132.

Mihalache, R. M. (2012), “Coordinate Transformation for Integrating Map Information in The New Geocentric European System Using Artificial Neural Networks”, GeoCAD, pp. 1-9.

Molodensky, M. S., Yeremeyev, V. and Yurkina, M. (1962), “Methods for Study of the External Gravitational Field and Figure of the Earth”, Technical Report Office of Technical services, US Department of Commerce, Israel Program for Scientific Translation, Jerusalem, Israel, 248 pp.

Muller, V. A. and Hemond, F. H. (2013), “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”, Talanta, Vol. 117, pp. 112–118.

Park, J. and Sandberg, I.W. (1991), “Universal Approximation Using Radial Basis Function Networks”, Neural Computation, Vol. 3, No. 2, pp. 246-257.

Poku-Gyamfi, Y. (2009), “Establishment of GPS Reference Network in Ghana”, PhD Dissertation, Universitat der Bundeswehr Munchen, Germany, pp. 1-177.

Samui, P. (2012), “Slope Stability Analysis Using Multivariate Adaptive Regression Spline”, Metaheuristics in Water, Geotechnical and Transportation Engineering, Vol. 14, pp. 327-342.

Samui, P. and Kurup, P. (2012), “Multivariate Adaptive Regression Spline and Least Square Support Vector Machine for Prediction of Undrained Shear Strength of Clay”, International Journal of Applied Metaheuristic Computing, Vol. 3, No. 2, pp. 33-42.

Schuh, H., Ulrich, M., Egger, D., Muller, J. and Schwegmann, W. (2002), “Prediction of Earth Orientation Parameters by Artificial Neural Networks”, Journal of Geodesy, Vol. 76, Vol. 5, pp. 247–258.

Sorkhabi, O. M. (2015), “Geoid Determination Based on Log Sigmoid Function of Artificial Neural Networks: (A case study: Iran)”, Journal of Artificial Intelligence in Electrical Engineering, Vol. 3, No. 12, pp. 18-24.

Thomas, G., Sannier, C., Taylor, J. C. and Koh, A. (1999), “Estimating the Datum Transformation Parameters Associated with the Ghana National Mapping System”, DFID Project R6880, pp. 1-14.

Thomas, G., Sannier, C. A. D. and Taylor, J. C. (2000), “Mapping Systems and CIS: A Case Study using the Ghana National Grid”, The Geographical Journal, Vol. 166, No. 4, pp. 306-311.

Tierra, A. and Romero, R. (2014), “Planes Coordinates Transformation between PSAD56 to SIRGAS using a Multilayer Artificial Neural Network”, Geodesy and Cartography, Vol. 63, No. 2, pp. 199-209.

Tierra, A., Dalazoana R., and De Freitas, S. (2008), “Using an Artificial Neural Network to Improve the Transformation of Coordinates between Classical Geodetic Reference Frames.” Computers and Geosciences, Vol. 34, No. 3, pp. 181-189.

Tierra, A. R. and De Freitas, S. R. C. (2005), “Artificial Neural Network: A Powerful Tool for Predicting Gravity Anomaly from Sparse Data”, Gravity, Geoid and Space Missions, International Association of Geodesy Symposia, Springer, US, pp. 208-213.

Tierra, A. R., De Freitas, S. R. C. and Guevara, P. M. (2009), “Using an Artificial Neural Network to Transformation of Coordinates from PSAD56 to SIRGAS95”, Geodetic Reference Frames, International Association of Geodesy Symposia, Vol. 134, pp. 173-178.

Turgut, B. (2010), “A Back-Propagation Artificial Neural Network Approach for Three-Dimensional Coordinate Transformation” Science and Research Essay, Vol. 5, No. 21, pp. 3330-3335.

Veis, G. (1960), “Geodetic uses of Artificial Satellites”, Smithsonian contributions to Astrophysics, Vol. 3, pp. 1-95.

Wolf, H. (1963), “Geometric Connection and Reorientation of Three Dimensional Triangulation Nets”, Bulletin Geodesique, Vol. 68, No. 1, pp. 165-169.

Wu, C. H., Chou, H. J. and Su, W. H. (2008), “Direct Transformation of Coordinates for GPS Positioning Using the Techniques of Genetic Programming and Symbolic Regression” Engineering Applications of Artificial Intelligence, Vol. 21, No. 8, pp. 1347-1359.

Yilmaz, I. and Gullu, M. (2012), “Georeferencing of Historical Maps Using Back Propagation Artificial Neural Network”, Experimental Techniques, Vol. 3, No. 5, pp. 15-19.

Yilmaz, M. (2013), “Artificial Neural Networks Pruning Approach for Geodetic Velocity Field Determination”, Boletim de Ciências Geodésicas, Vol. 19, No. 4, pp. 558-573.

Zaletnyik, P. (2004), “Coordinate Transformation with Neural Networks and with Polynomials in Hungary”, International Symposium on Modern Technologies, Education and Professional Practice in Geodesy and Related Fields, Sofia, Bulgaria, pp. 471-479.

Zhang, W. and Goh, A. T. C. (2016), “Multivariate Adaptive Regression Splines and Neural Network Models for Prediction of Pile Drivability”, Geoscience Frontiers, Vol. 7, No. 1, pp. 45-52.

Ziggah, Y. Y., Youjian, H., Odutola, C. A., and Fan, D. L. (2013a), “Determination of GPS Coordinate Transformation Parameters of Geodetic Data Between Reference Datums - A Case Study of Ghana Geodetic Reference Network”, International Journal of Engineering Sciences and Research Technology, Vol. 2, No. 4, pp. 2277-9655.

Ziggah, Y. Y., Youjian, H., Odutola, C. A. and Nguyen, T. T. (2013b), “Accuracy Assessment of Centroid Computation Methods in Precise GPS Coordinates Transformation Parameters Determination- A Case Study, Ghana”, European Scientific Journal, Vol. 9, No. 15, pp. 1857-7431.

Ziggah, Y. Y., Akwensi, P. H. and Annan, R. F. (2016a), “Plane Coordinate Transformation Using General Least Squares Approach – A Case Study of Ghana Geodetic Reference Network”, 4th UMaT Biennial International Mining and Mineral Conference, 2016 August, Tarkwa, Ghana, pp. 68-77.

Ziggah, Y. Y., Yakubu, I. and Kumi-Boateng, B. (2016b), “Analysis of Methods for Ellipsoidal Height Estimation – The Case of a Local Geodetic Reference Network”, Ghana Mining Journal, Vol. 16, No. 2, pp. 1-9.

Ziggah, Y. Y., Youjian, H., Yu, X. and Laari, P. B. (2016c), “Capability of Artificial Neural Network for Forward Conversion of Geodetic Coordinates (ϕ, λ, h ) to Cartesian Coordinates (X, Y, Z)”, Mathematical Geosciences, Vol. 48, No. 6, pp. 687-721.

Ziggah, Y. Y. and Yakubu, I. (2017), “Alternative Methods of Determining Translation Parameters for Geocentric Translation Model Applications”, Ghana Journal of Technology, Vol. 2, No. 1, pp. 38 - 50.

Ziggah, Y. Y., Ayer, J. and Laari, P.B. (2017a), “Coordinate Transformation Using Featherstone and Vaníček Proposed Approach – A Case Study of Ghana Geodetic Reference Network, Geoplanning: Journal of Geomatics and Planning, Vol. 4, No. 1, pp. 19-26.

Ziggah, Y. Y., Youjian, H., Laari, P.B. and Hui, Z. (2017b), “Novel Approach to Improve Geocentric Translation Model Performance Using Artificial Neural Network Technology”, Boletim de Ciências Geodésicas, Vol. 23, No. 1, pp. 213-233.


Refbacks

  • There are currently no refbacks.