We have developed a novel approach for seismic modeling combining conventional finite differences with deep neural networks. The method includes the following steps. First, a training data set composed of a small number of common-shot gathers is generated. The data set is computed using a finite-difference scheme with fine spatial and temporal discretization. Second, the entire set of common-shot seismograms is generated using an inaccurate numerical method, such as a finite-difference scheme on a coarse mesh. Third, the numerical dispersion mitigation neural network is trained and applied to the entire data set to suppress the numerical dispersion. We have tested the approach on two 2D models, illustrating a significant acceleration of seismic modeling.

You do not have access to this content, please speak to your institutional administrator if you feel you should have access.