LAUSR

Surface wave exploration has been increasingly used in near-surface geophysical investigations. However, the accuracy and efficiency of picking dispersion curves are the key to surface wave inversion. Traditional dispersion curve extraction requires manual picking, and the extraction accuracy and efficiency depend on the experience and knowledge of the interpreters. Therefore, developing a fast, high-precision, and intelligent dispersion curve extraction method is urgent. This article improves the structure and output of the U-Net neural network and regards the picking process of dispersion curves as an image classification problem, which quickly and accurately extracts dispersion curves from dispersion energy images. After combining the dispersion energy images of synthetic seismic data with the manually extracted dispersion curve and the theoretical dispersion curve obtained by the Schwab–Knopoff algorithm, the energy image and dispersion curve extracted manually (ICM) training set and the energy image and dispersion curve calculated by the Schwab–Knopoff algorithm (ICS) training set are created. The synthetic data tests verify the feasibility of the improved U-Net neural network for automatically picking multimode dispersion curves. The dispersion curve picking results corresponding to two different training sets reveal that the U-Net network model obtained from the ICS training sets exhibits better extraction accuracy. Additionally, we analyze the influence of the sample number of the training set on the dispersion curve picking effect of the improved U-Net and conclude that the improved U-Net network has the advantages of a low training set size requirement and a high dispersion curve extraction accuracy. Finally, the trained network extracts the dispersion curves of two groups of measured surface wave data and obtains plausible extraction results, further proving the proposed method’s effectiveness.