Cellular Neural Network for Seismic Horizon Picking
Kou‐Yuan Huang, Chin-Hua Chang, Wen-Shiang Hsieh, Shan‐Chih Hsieh, L.K. Wang, Fan-Jen Tsai · 2005
Cellular neural network has the property of local connection. We use this property for seismic horizon linking. The constraint conditions for detecting seismic horizons are used to construct the Lyapunov energy function. The connection weights between neurons are extracted from Lyapunov energy function. Substitute the connection weights into the equation of motion, the next state value of each neuron can be calculated. After training, we apply the equation of motion to seismic horizon linking. From the experimental results in seismic bright spot pattern, the picked horizons can match the visual inspection. The automatic seismic horizon picking can help the seismic data processing and improve the seismic interpretation.