Super-Resolution of Elliptic PDE Solutions Using Least Squares Support Vector Regression

TL;DR

This paper introduces a hybrid FEM-LSSVR method that enhances the resolution of elliptic PDE solutions, providing high-accuracy, closed-form solutions that improve upon standard FEM results with minimal additional implementation effort.

Contribution

The paper presents a novel hybrid approach combining FEM with LSSVR using Legendre kernels for super-resolution of PDE solutions, enabling high-order accuracy from low-order FEM codes.

Findings

Achieves significantly higher accuracy than base FEM solutions.

Provides comparable accuracy to high-order FEM with lower computational cost.

Demonstrates robustness across four elliptic boundary value problems.

Abstract

A hybrid computational approach that integrates the finite element method (FEM) with least squares support vector regression (LSSVR) is introduced to solve partial differential equations. The method combines FEM's ability to provide the nodal solutions and LSSVR with higher-order Legendre polynomial kernels to deliver a closed-form analytical solution for interpolation between the nodes. The hybrid approach implements element-wise enhancement (super-resolution) of a given numerical solution, resulting in high resolution accuracy, while maintaining consistency with FEM nodal values at element boundaries. It can adapt any low-order FEM code to obtain high-order resolution by leveraging localized kernel refinement and parallel computation without additional implementation overhead. Therefore, effective inference/post-processing of the obtained super-resolved solution is possible. Evaluation results show that the hybrid FEM-LSSVR approach can achieve significantly higher accuracy compared to the base FEM solution. Comparable accuracy is a achieved when comparing the hybrid solution with a standalone FEM result with the same polynomial basis function order. The convergence studies were conducted for four elliptic boundary value problems to demonstrate the method's ability, accuracy, and reliability. Finally, the algorithm can be directly used as a plug-and-play method for super-resolving low-order numerical solvers and for super-resolution of expensive/under-resolved experimental data.