Seismic wave propagation forms the basis for most aspects of seismological research, yet solving the wave equation is a major computational burden that inhibits the progress of research. This is exacerbated by the fact that new simulations must be performed whenever the velocity structure or source location is perturbed. Here, we explore a prototype framework for learning general solutions using a recently developed machine learning paradigm called neural operator. A trained neural operator can compute a solution in negligible time for any velocity structure or source location. We develop a scheme to train neural operators on an ensemble of simulations performed with random velocity models and source locations. As neural operators are grid free, it is possible to evaluate solutions on higher resolution velocity models than trained on, providing additional computational efficiency. We illustrate the method with the 2D acoustic wave equation and demonstrate the method’s applicability to seismic tomography, using reverse-mode automatic differentiation to compute gradients of the wavefield with respect to the velocity structure. The developed procedure is nearly an order of magnitude faster than using conventional numerical methods for full waveform inversion.

The Community Seismic Network (CSN) is currently a 500‐element strong‐motion network located in the Los Angeles area of California (see Fig. 1). The sensors in the network are low‐cost microelectromechanical (MEM) accelerometers that are capable of recording on scale up to accelerations of ±2g. The primary product of the network is a set of measurements of ground shaking in the seconds following a major earthquake. An example of this is shown in Figure 2. The shaking information will be contributed to U.S. Geological Survey products such as ShakeMap (Wald et al., 1999) and...

Seismic waveform modeling is a powerful tool for determining earth structure models and unraveling earthquake rupture processes, but it is usually computationally expensive. We introduce a scheme to vastly accelerate these calculations with a recently developed machine learning paradigm called the neural operator. Once trained, these models can simulate a full wavefield at negligible cost. We use a U-shaped neural operator to learn a general solution operator to the 2D elastic wave equation from an ensemble of numerical simulations performed with random velocity models and source locations. We show that full waveform modeling with neural operators is nearly two orders of magnitude faster than conventional numerical methods, and more importantly, the trained model enables accurate simulation for velocity models, source locations, and mesh discretization distinctly different from the training dataset. The method also enables convenient full-waveform inversion with automatic differentiation.

Summary. Receiver functions (RFs) from teleseismic events recorded by the NARS-Baja array were used to map crustal thickness in the continental margins of the

SUMMARY: Numerical simulations of seismic wave propagation in heterogeneous 3-D media are central to investigating subsurface structures and understanding earthquake processes, yet are computationally expensive for large problems. This is particularly problematic for full-waveform inversion (FWI), which typically involves numerous runs of the forward process. In machine learning there has been considerable recent work in the area of operator learning, with a new class of models called neural operators allowing for data-driven solutions to partial differential equations. Recent work in seismology has shown that when neural operators are adequately trained, they can significantly shorten the compute time for wave propagation. However, the memory required for the 3-D time domain equations may be prohibitive. In this study, we show that these limitations can be overcome by solving the wave equations in the frequency domain, also known as the Helmholtz equations, since the solutions for a set of frequencies can be determined in parallel. The 3-D Helmholtz neural operator is 40 times more memory-efficient than an equivalent time-domain version. We use a Helmholtz neural operator for 2-D and 3-D elastic wave modelling, achieving two orders of magnitude acceleration compared to a baseline spectral element method. The neural operator accurately generalizes to variable velocity structures and can be evaluated on denser input meshes than used in the training simulations. We also show that when solving for wavefields strictly at the free surface, the accuracy can be significantly improved via a graph neural operator layer. In leveraging automatic differentiation, the proposed method can serve as an alternative to the adjoint-state approach for 3-D FWI, reducing the computation time by a factor of 350.