> For the complete documentation index, see [llms.txt](https://smousavi05.gitbook.io/mlseismology/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://smousavi05.gitbook.io/mlseismology/seismological-tasks/dispersion-curve-extraction.md).

# Dispersion Curve Extraction

The extraction and classification of dispersion curves (the medium-determined intrinsic relation between surface waves in terms of frequency and phase velocity) is a key step in the inversion of shear-wave velocity using surface-wave methods.

### **Used ML Approaches:**

* Artificial Neural Networks

### **Used Neural Networks:**

* CNN
* U-Net
* VGG

### Used Learning Procedures:

* Supervised Learning
* Unsupervised Learning

### References:

1. Zhang, X., Jia, Z., Ross, Z. E., & Clayton, R. W. (2020). Extracting dispersion curves from ambient noise correlations using deep learning. IEEE Transactions on Geoscience and Remote Sensing, 58(12), 8932-8939.
2. Dai, T., Xia, J., Ning, L., Xi, C., Liu, Y., & Xing, H. (2021). Deep learning for extracting dispersion curves. Surveys in Geophysics, 42(1), 69-95.
3. Dong, S., Li, Z., Chen, X., & Fu, L. (2021). DisperNet: An Effective Method of Extracting and Classifying the Dispersion Curves in the Frequency–Bessel Dispersion Spectrum. Bulletin of the Seismological Society of America.