GPS-derived Geoid using Artificial Neural Network and Least Squares Collocation

Abstract The geoidal undulations are needed for determining the orthometric heights from the Global Positioning System GPS-derived ellipsoidal heights. There are several methods for geoidal undulation determination. The paper presents a method employing the Artificial Neural Network (ANN) approximation together with the Least Squares Collocation (LSC). The surface obtained by the ANN approximation is used as a trend surface in the least squares collocation. In numerical examples four surfaces were compared: the global geopotential model (EGM96), the European gravimetric quasigeoid 1997 (EGG97), the surface approximated with minimum curvature splines in tension algorithm and the ANN surface approximation. The effectiveness of the ANN surface approximation depends on the number of control points. If the number of well-distributed control points is sufficiently large, the results are better than those obtained by the minimum curvature algorithm and comparable to those obtained by the EGG97 model.

[1]  N. K. Pavlis,et al.  The Development of the Joint NASA GSFC and the National Imagery and Mapping Agency (NIMA) Geopotential Model EGM96 , 1998 .

[2]  Walter H. F. Smith,et al.  Gridding with continuous curvature splines in tension , 1990 .

[3]  D. Rumelhart.  Parallel Distributed Processing Volume 1: Foundations , 1987 .

[4]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[5]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[6]  Stanley K. Jordan,et al.  Self‐consistent statistical models for the gravity anomaly, vertical deflections, and undulation of the geoid , 1972 .

[7]  Wolfgang Torge,et al.  The European Gravimetric Quasigeoid EGG97 - An IAG Supported Continental Enterprise - , 1998 .

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  Eitaro Aiyoshi,et al.  A distributed model of the saccade system: simulations of temporally perturbed saccades using position and velocity feedback , 1999, Neural Networks.

[10]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[11]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[12]  Vasant Honavar,et al.  Adaptive learning rate for increasing learning speed in backpropagation networks , 1993, Defense, Security, and Sensing.

[13]  James Seager,et al.  Modelling geoid undulations with an artificial neural network , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[14]  Tamás D. Gedeon,et al.  Simulated annealing and weight decay in adaptive learning: the SARPROP algorithm , 1998, IEEE Trans. Neural Networks.

[15]  Edward M. Mikhail,et al.  Observations And Least Squares , 1983 .

[16]  H. Moritz.  Advanced Physical Geodesy , 1980 .