Separation of multi‐mode surface waves by supervised machine learning methods

Abstract

A B S T R A C TLogistic regression, neural networks and support vector machines are tested for their effectiveness in isolating surface waves in seismic shot records. To distinguish surface waves from other arrivals, we train the algorithms on three distinguishing features of surface-wave dispersion curves in the k − ω domain: spectrum coherency of the trace's magnitude spectrum, local dip and the frequency range for a fixed wavenumber k in the spectrum. Numerical tests on synthetic data show that the kernel-based support vector machines algorithm gives the highest accuracy in predicting the surface-wave window in the k − ω domain compared to neural networks and logistic regression. This window is also used to automatically pick the fundamental dispersion curve. The other two methods correctly pick the low-frequency part of the dispersion curve but fail at higher frequencies where there is interference with higher-order modes.

Superpixel-Based Convolutional Neural Network for Georeferencing the Drone Images

“…The effect of this voting process on the entire image can be seen in Fig. 14 The CNN labels belonging to the same superpixels should have the same labels; so the labels in each superpixel are merged into one label that represents the majority class in the superpixel. Fig.…”

“…Given an aerial image, the pixel labeling approaches classify each pixel to get a binary classification of This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ the image for a single object class [13], [14] or a multiclass classification to get a complete semantic segmentation of the image into classes such as roads, grasses, and cars [15]. In our article, both cases are studied for detecting the objects in the aerial image.…”

An Effective Method to Extract Overtones of Surface Wave From Array Seismic Records of Earthquake Events

“…10.1029/2019JB018511 surface wave separation (e.g., Hu & Zheng, 2019;Li et al, 2020). We believe that through a series of tests on synthetic and real data, the combination of new technologies and the MWFJ method can effectively improve the efficiency of dispersion curve extraction in the future.…”

Wave‐Equation Dispersion Inversion of Guided P Waves in a Waveguide of Arbitrary Geometry

“…For large data sets, an adaptive machine-learning algorithm can be used to efficiently and accurately pick dispersion curves (J. Li et al, 2018). 3.…”

“…The traces recorded within about one fourth of the wavelength from the source are excluded. For large data sets, an adaptive machine‐learning algorithm can be used to efficiently and accurately pick dispersion curves (J. Li et al, ). Use equation to compute the weighted data , which is then used for computing the backprojected data b ( x , s ) ω in equation . The source field f ( x , s ) ω in equation computed by a finite-difference solution to the elastic wave equation. Employ the zero‐lag cross correlation of the forward‐ and backward‐propagated wavefields to calculate the misfit gradient (see equation for each shot gather. Use equation with a line search to get the update for the P velocity.…”