Extraction of Mine Deposit Areas in Sivas-Divrigi Region Using Cellular Neural Network Approach


ALBORA A. M. , UÇAN O. M. , ÖZMEN A.

EUROPEAN GEOPHYSICAL SOCIETY XXV GENERAL ASSEMBLY, France, 1 - 04 April 2000, vol.2, pp.1-2

  • Publication Type: Conference Paper / Summary Text
  • Volume: 2
  • Country: France
  • Page Numbers: pp.1-2

Abstract

 In this paper,   Cellular Neural Network (CNN)  has been applied to real data of Sivas-Divrigi Bouguer anomaly separation problem, the first time in the literature. The advantages of this method are that it introduces little distortion to the shape of the original image and that it is not effected significantly by factors such as the overlap power spectra of  residual fields. Satisfactory and practical results have been  found. The placement and density of the mine have been detected correctly. The research has been are evaluated on real time.  Cellular Neural Network is a large-scale non-linear analog circuits which processes signals in real time (Leon O. Chua et’al, 1998).  Like cellular automata, it is made of massive aggregate of regularly spaced circuits clones, called cells, which communicate with each other directly only through its nearest neighbours. The adjacent cells can interact directly with each other.  Cells not directly connected together may affect each other indirectly because of the propagation effects of the continous-time dynamics of cellular neural networks. We call the cell on the ith row and  jth column cell C(i,j) as in Figure 1. Now let us define, neighborhood of C(i,j). We have applied CNN approach on the real field at eastern of Turkey, Sivas which is an important mine center. Satisfactory and practical results have been  found. The placement and density of the mine have been detected correctly