Hopfield neural network for seismic velocity picking

Author

Kou-Yuan Huang ; Jia-Rong Yang

Author_Institution

Dept. of Comput. Sci., Nat. Chiao Tung Univ., Hsinchu, Taiwan

fYear

2014

fDate

6-11 July 2014

Firstpage

1146

Lastpage

1153

Abstract

The Hopfield neural network (HNN) is adopted for velocity picking in the time-velocity semblance image of seismic data. A Lyapunov function in the HNN is set up from the velocity picking problem. We use the gradient descent method to decrease the Lyapunov function and derive the equation of motion. According to the equation of motion, each neuron is updated until no change. The converged network state represents the best polyline in velocity picking. We have experiments on simulated and real seismic data. The picking results are good and close to the human picking results.

Keywords

Hopfield neural nets; geophysics computing; gradient methods; seismology; velocity; HNN; Hopfield neural network; Lyapunov function; best polyline; converged network state; equation of motion; gradient descent method; neuron; seismic data; seismic velocity picking problem; time-velocity semblance image; Equations; Hopfield neural networks; Lyapunov methods; Mathematical model; Neurons; Receivers; Stacking; Hopfield neural network; Lyapunov function; equation of motion; seismic velocity picking; semblance image;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks (IJCNN), 2014 International Joint Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4799-6627-1

Type

conf

DOI

10.1109/IJCNN.2014.6889512

Filename

6889512