High-Dimensional Wavefield Solutions Using Physics-Informed Neural Networks with Frequency-Extension
KAUST DepartmentKing Abdullah University of Science and Technology
Biological and Environmental Science and Engineering (BESE) Division
Physical Science and Engineering (PSE) Division
Earth Science and Engineering Program
Permanent link to this recordhttp://hdl.handle.net/10754/678309
MetadataShow full item record
AbstractHigh-dimensional wavefield solutions, like Green’s functions, are important to waveform inversion and imaging applications. Their numerical representations often require large memory or disk space allocation, and thus, are computationally intensive to access. Physics-informed neural networks (PINNs) have shown considerable potential, as neural solvers, to add flexibility and scalability to the solution. However, when dealing with high-dimensional wavefields, their accuracy and the training cost limit their applicabilities. Thus, based on the single reference frequency loss function, we propose a PINN implementation for wavefield solutions that utilizes frequency extension and neuron splitting. As a result, the neural network model can grow in size to accommodate the increase in frequency range while leveraging the pre-trained model for the narrow frequency-range wavefield, resulting in fast convergence and high-accuracy solutions. Numerical results show that, compared to the commonly used PINN with the random initialization, the proposed PINN exhibits notable superiority in terms of convergence and accuracy.
CitationHuang, X., Alkhalifah, T., & Wang, F. (2022). High-Dimensional Wavefield Solutions Using Physics-Informed Neural Networks with Frequency-Extension. 83rd EAGE Annual Conference & Exhibition. https://doi.org/10.3997/2214-4609.202210542
SponsorsWe thank KAUST for its support and the SWAG group for the collaborative environment. This work utilized the resources of the Supercomputing Laboratory at KAUST, and we are grateful for that.
Conference/Event name83rd EAGE Annual Conference & Exhibition