Inverse Scattering of a Dielectric Sphere Partially Buried in a Ground Plane Using a Radial Basis Function Network
Keywords:
Inverse Scattering of a Dielectric Sphere Partially Buried in a Ground Plane Using a Radial Basis Function NetworkAbstract
An analytic solution of the problem of electromagnetic scattering by a dielectric spherical scatterer resting on, or partially buried in, an infinite perfectly conducting ground plane is approximated by partially truncated sphere and is formulated using the method of images. The scattered field coefficients are solved exactly so that the scattered field can be evaluated everywhere. In particular, the scattering cross section can be calculated as a function of the sphere radius and permittivity as well as the truncated sphere distance for any specified angle of incidence. The solution of this problem is relevant to analyze the scattering by complex threedimensional bodies, plastic mines, icebergs, rough surfaces, etc., in which the flat background can be modeled by the ground plane while the complex body can be simulated by a sphere or a system of spheres partially truncated and resting on the ground plane. In order to solve the inverse scattering problem, we employ a radial basis function network to take the scattered field complex coefficients for the TE and TM polarization case as the network inputs to predict the three outputs of the electrical radius, burial distance, and relative permittivity of the sphere. The trained network is able to retrieve the three aforementioned parameters from new data which is different from the learning data.
Downloads
References
A.-K. Hamid, and M. Hamid, “Electromagnetic
scattering by a dielectric sphere partially buried in
an infinite plane,” Canadian Journal of Physics,
vol. 80, pp. 979-986, 2002.
C. Eftimiu, “Direct and inverse scattering by a
sphere of variable index of refraction,” Journal of
Mathematical Physics, vol. 23, no. 11, pp. 2140-
1982.
ACES JOURNAL, VOL. 19, NO. 3, NOVEMBER 2004
J. Sylvester, and D. P. Winebrenner, “Linear and
nonlinear inverse scattering,” SIAM Journal of
Applied Mathematics 59(2), pp. 669-699, 1998.
I. T. Rekanos, T. V. Yioultsis & T.D.Tsiboukis “
Inverse scattering using the finite-element method
and a nonlinear optimization Technique ”, IEEE
Trans. On Microwave Theory and Techniques, vol.
, no. 3, pp. 336-344,1999.
A-K Hamid, “A neural-network approach to the
inverse-scattering problem from a circular
conducting cylindrical scatterer,” Microwave and
Optical Tech. Letters, vol. 13, no. 6, pp. 380-382,
E. Bermani, S. Caorsi, M. Raffetto, “An inverse
scattering approach based on a neural network
technique for the detection of dielectric cylinders
buried in a lossy half-space,” Progress in
Electromagnetics Research, no. 26, pp. 69-90,
S. Caorsi and P. Gamba, “Electromagnetic
detection of dielectric cylinder by a neural network
approach,” IEEE Trans. on Geoscience and
Remote Sensing, vol. 37, 820-827, 1999.
X. Gong and Y. Wang, “A neural network
approach to the microwave inverse scattering
problem with edge-preserving regularization,”
Radio Science, vol. 36, no. 5, pp. 825-832, 2001.
S. Chen, C. F. N. Cowan, and P. M. Grant.
“Orthogonal least squares learning for radial basis
function networks,” IEEE Trans. On Neural
Networks, vol. 2, no. 2, pp. 302-309, 1991.
Y. L. Xu, ”Electromagnetic scattering by an
aggregate of spheres: Far field,” Appl. Optics. vol.
, pp. 9496-9508, 1997.
J. Park and J. W. Sandbeg, “Universal
approximation using radial basis functions
network,” Neural Computation, vol. 3, pp. 246-
, 1991.
T. Poggio and F. Girosi, (1990) “Networks for
approximation and learning,” Proc. IEEE, vol. 78,
no. 9, pp. 1481-1497.
J. A. Stratton, Electromagnetic Theory, McGraw-
Hill, New York, 1941.
P. Bhartia, R. A. Ross and M. Hamid, “Ray optical
scattering by two spheres”, Arch. Elekt. Ubertrag.,
vol. 24, pp. 215-222, 1970.
R. A. Horn and C. R. Johnson. “Matrix Analysis,”
Cambridge University Press, Cambridge, UK,