TRAINING OF CELLULAR NEURAL NETWORKS AND APPLICATION TO GEOPHYSICS

Year 2013, Volume: 26 Issue: 1, 53 - 64, 06.07.2013

Davut Aydogan

Abstract

In this study, to determine horizontal location of subtle boundaries in the gravity anomaly maps, an image processing

method known as Cellular Neural Networks (CNN) is used. The method is a stochastic image processing method

based on close neighborhood relationship of the cells and optimization of A, B and I matrices known as cloning templates.

Template coefficients of continuous-time cellular neural networks (CTCNN) and discrete-time cellular neural

networks (DTCNN) in determining bodies and edges are calculated by particle swarm optimization (PSO) algorithm.

In the first step, the CNN template coefficients are calculated. In the second step, DTCNN and CTCNN outputs are

visually evaluated and the results are compared with each other. The method is tested on Bouguer anomaly map of

Salt Lake and its surroundings in Turkey. Results obtained from the Blakely and Simpson algorithm are compared

with the outputs of the proposed method and the consistence between them is examined. The cases demonstrate that

CNN models can be used in visual evaluation of gravity anomalies.

Keywords

Cellular Neural Network, Particle Swarm Optimization

References

• Sanyi, Y., Shangxu, W., Nan, T., 2009, Swarm intelligence optimization and its application in geophysical data inversion, Applied Geophysics 6, 2, 166 – 174.