DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
This addresses the problem of efficiently solving PDEs for researchers in computational physics and engineering, representing a novel method for a known bottleneck.
The paper tackled solving partial differential equations in sparse data regimes by introducing DeepVekua, a hybrid architecture that unifies geometric deep learning with spectral analysis, resulting in a 100x improvement over spectral baselines.
We present DeepVekua, a hybrid architecture that unifies geometric deep learning with spectral analysis to solve partial differential equations (PDEs) in sparse data regimes. By learning a diffeomorphic coordinate transformation that maps complex geometries to a latent harmonic space, our method outperforms state-of-the-art implicit representations on advection-diffusion systems. Unlike standard coordinate-based networks which struggle with spectral bias, DeepVekua separates the learning of geometry from the learning of physics, solving for optimal spectral weights in closed form. We demonstrate a 100x improvement over spectral baselines. The code is available at https://github.com/VladimerKhasia/vekuanet.