Journal
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
Volume -, Issue -, Pages 2781-2785Publisher
IEEE
DOI: 10.1109/ICIP46576.2022.9897269
Keywords
Waveform imaging; Neural networks; partial differential equations
Funding
- KAUST
Ask authors/readers for more resources
Imaging is a crucial task in various fields, and the exploding reflector assumption provides a direct imaging approach for zero-offset data. However, aliasing problems arise when the data are coarsely sampled. By formulating the frequency-domain wavefield as a neural network function, the physics-informed neural network framework enables subsurface imaging.
Imaging is a crucial inversion-based task in fields ranging from medical to structure investigations, and Earth discovery. The exploding reflector assumption provides a direct imaging approach for zero-offset (coincident source-receiver) data, like ground penetrating radar (GPR) data. In imaging, however, we face aliasing problems when the data are coarsely sampled. Formulating the corresponding frequency-domain wavefield as a neural network (NN) function of the lateral and depth coordinates, as well as frequency, allows us to use the physics-informed neural network (PINN) framework to obtain images of the subsurface. In this case, we use a modified Helmholtz equation that incorporates the data on the Earth surface (hard constraint) as the loss function to optimize the NN function. This modified Helmholtz formulation allows us to avoid the inherent weaknesses that PINN has in handling boundary conditions, like the data on the surface as an additional loss term. The frequency dimension allows for image reconstruction by directly summing the wavefield over frequencies (the zero-time imaging condition). This zero-offset implementation serves as a proof of concept for later extensions to prestack data using the double square-root equation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available