DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
By: Vladimer Khasia
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.
Similar Papers
The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation
Machine Learning (CS)
Solves hard science problems with fewer computer parts.
The Vekua Layer: Exact Physical Priors for Implicit Neural Representations via Generalized Analytic Functions
Machine Learning (CS)
Lets computers learn shapes from just a few points.
Separated-Variable Spectral Neural Networks: A Physics-Informed Learning Approach for High-Frequency PDEs
Machine Learning (CS)
Solves wiggly physics equations 1000 times better