Physics-Informed Neural Network Super Resolution for Advection-Diffusion Models
This work addresses the challenge of enhancing spatial resolution and handling missing data in domain-specific applications like atmospheric science, representing an incremental advancement over standard super-resolution methods.
The paper tackles the problem of reconstructing high-resolution images from low-resolution data in atmospheric pollution plume models by using physics-informed neural networks, demonstrating an 11% improvement in signal-to-noise ratio when incorporating physical equations with 40% pixel loss.
Physics-informed neural networks (NN) are an emerging technique to improve spatial resolution and enforce physical consistency of data from physics models or satellite observations. A super-resolution (SR) technique is explored to reconstruct high-resolution images ($4\times$) from lower resolution images in an advection-diffusion model of atmospheric pollution plumes. SR performance is generally increased when the advection-diffusion equation constrains the NN in addition to conventional pixel-based constraints. The ability of SR techniques to also reconstruct missing data is investigated by randomly removing image pixels from the simulations and allowing the system to learn the content of missing data. Improvements in S/N of $11\%$ are demonstrated when physics equations are included in SR with $40\%$ pixel loss. Physics-informed NNs accurately reconstruct corrupted images and generate better results compared to the standard SR approaches.