Extracting Dispersion Curves From Ambient Noise Correlations Using Deep Learning
We present a machine learning approach to classify the phases of surface wave dispersion curves. Standard frequency-time analysis (FTAN) analysis of seismograms observed on an array of receivers is converted into an image, of which each pixel is classified as fundamental mode, first overtone, or noise. We use a convolutional neural network (U-Net) architecture with a supervised learning objective and incorporate transfer learning. The training is initially performed with synthetic data to learn coarse structure, followed by fine-tuning of the network using approximately 10% of the real data based on human classification. The results show that the machine classification is nearly identical to the human picked phases. Expanding the method to process multiple images at once did not improve the performance. The developed technique will facilitate the automated processing of large dispersion curve data sets.
Additional Information© 2020 IEEE. Manuscript received February 5, 2020; revised April 29, 2020; accepted April 29, 2020. Date of publication May 25, 2020; date of current version November 24, 2020. This work was supported in part by NSF/EAR under Grant 1520081. The authors would like to thank M. Mousavi and an Anonymous Reviewer for their constructive reviews of this article. They would like to thank Signal Hill Petroleum for permission to use the Long Beach Array and the Southern California Seismic Network for providing data from the broadband stations. They would also like to thank Y. Yue for helpful discussions.
Submitted - 2002.02040.pdf