Determination of seismic wave velocities on the ground using artificial neural networks

Abstract

Objective. The purpose of the study is to determine the velocities of seismic waves on the ground.Method. To determine the velocities of seismic waves in different parts of the earth's crust, using a sample obtained by mathematical modeling, an artificial neural network was trained. Using at the input of the trained neural network, the real values of the differences in the times of arrival of seismic waves on the ground, we obtain at its output the values of the velocities of seismic waves on the ground.Result. A method for determining the velocities of seismic waves on the ground using artificial neural networks is proposed. Dependences of the root-mean-square error in determining the velocities of seismic waves on the ground on the training epoch, as well as the distribution of errors in determining the coordinates of the earthquake hypocenter using the obtained information about the structure of the earth, are obtained.Conclusion. The proposed method makes it possible to determine the structure of the earth's crust more accurately than previously proposed mathematical methods.

Keywords

• neural network
• seismic wave velocities
• snell's law
• seismology
• seismic sensor