SfNet

We proposed a novel deep-learning method to invert surface-wave dispersions and obtained an updated <em>Vs</em> model of the Chinese continent. Training a DL inversion network usually requires large amount of complex velocity models, which is labor-intensive and expensive to acquire. Here we relied on synthetics generated automatically from various spline-based <em>Vs</em> models instead of directly using the existing<em> Vs</em> models of an area to build the training dataset, which enhances the generalization of the DL method. In addition, we used a random sampling strategy of the dispersion periods in the training dataset, which alleviates the problem that the real data used must be sampled strictly according to the periods of training dataset.