Learned frequency-domain scattered wavefield solutions using neural operators
Xinquan Huang, Tariq Alkhalifah
Abstract
SUMMARY Solving the wave equation is essential to seismic imaging and inversion. The numerical solution of the Helmholtz equation, fundamental to this process, often encounters significant computational and memory challenges. We propose an innovative frequency-domain scattered wavefield modelling method employing neural operators adaptable to diverse seismic velocities. The source location and frequency information are embedded within the input background wavefield, enhancing the neural operator’s ability to process source configurations effectively. In addition, we utilize a single reference frequency strategy, which enables scaling from larger domain forward modelling to higher frequency scenarios, thereby improving our method’s accuracy and generalization capabilities for larger domain applications. Several tests on the OpenFWI data sets and realistic velocity models validate the accuracy and efficacy of our method as a surrogate model, demonstrating its potential to address the computational and memory limitations of numerical methods.