Hopfield neural network can solve the optimization problem. We use Hopfield net to the seismic horizon picking. The peak position of each seismic wavelet is corresponding to one neuron. We transform the constraints of the detecting local horizon patterns and the constraints of extracting one horizon each time into the system energy function. From the theory of Hopfield net, changing the values of neurons can decrease the energy. The system will be stable until the values of neurons are not changed. One horizon is extracted by using the algorithm at each time. Remove the extracted horizon from the original seismic data and extract the next horizon until the last horizon is extracted. From the experimental results in bright spot, the picked horizons can match the visual inspection.
|Number of pages||5|
|State||Published - 1 Jan 1998|
|Event||Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA|
Duration: 4 May 1998 → 9 May 1998
|Conference||Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)|
|City||Anchorage, AK, USA|
|Period||4/05/98 → 9/05/98|