Separation of Bouguer anomaly map using cellular neural network

• Published in: Journal of applied geophysics Vol. 46; no. 2; pp. 129 - 142
• Main Authors: Albora, A.Muhittin, Ucan, Osman N., Ozmen, Atilla, Ozkan, Tulay
• Format: Journal Article
• Language: English
• Published: London Elsevier B.V 01.02.2001; Amsterdam Elsevier; New York, NY
• Subjects: Akdag Bouguer anomaly; Cellular Neural Network (CNN); Earth sciences; Earth, ocean, space; Exact sciences and technology; Internal geophysics; Sivas–Divrigi; Solid-earth geophysics, tectonophysics, gravimetry; Middle East; Turkey; Akdag Bouguer anomaly; Sivas–Divrigi; Cellular Neural Network (CNN); algorithms; exploration; testing; neural networks; gravimetry; well logs; mineralization; gravity anomalies; Asia; separation; iron; Bouguer anomalies; gravity survey maps
• ISSN: 0926-9851; 1879-1859
• DOI: 10.1016/S0926-9851(01)00033-7

In this paper, a modern image-processing technique, the Cellular Neural Network (CNN) has been firstly applied to Bouguer anomaly map of synthetic examples and then to data from the Sivas–Divrigi Akdag region. CNN is an analog parallel computing paradigm defined in space and characterized by the locality of connections between processing neurons. The behaviour of the CNN is defined by two template matrices and a template vector. We have optimised the weight coefficients of these templates using the Recurrent Perceptron Learning Algorithm (RPLA). After testing CNN performance on synthetic examples, the CNN approach has been applied to the Bouguer anomaly of Sivas–Divrigi Akdag region and the results match drilling logs done by Mineral Research and Exploration (MTA).