PINNup: Robust neural network wavefield solutions using frequency upscaling and neuron splitting
This work addresses a domain-specific problem in seismic modeling and inversion, offering an incremental improvement for handling high-frequency wavefields.
The paper tackles the challenge of accurately and efficiently solving high-frequency wavefield problems using physics-informed neural networks (PINNs) by introducing a method with frequency upscaling and neuron splitting, which achieves fast convergence and high accuracy, outperforming standard PINNs with random initialization.
Solving for the frequency-domain scattered wavefield via physics-informed neural network (PINN) has great potential in seismic modeling and inversion. However, when dealing with high-frequency wavefields, its accuracy and training cost limits its applications. Thus, we propose a novel implementation of PINN using frequency upscaling and neuron splitting, which allows the neural network model to grow in size as we increase the frequency while leveraging the information from the pre-trained model for lower-frequency wavefields, resulting in fast convergence to high-accuracy solutions. Numerical results show that, compared to the commonly used PINN with random initialization, the proposed PINN exhibits notable superiority in terms of convergence and accuracy and can achieve neuron based high-frequency wavefield solutions with a two-hidden-layer model.