Element learning: a systematic approach of accelerating finite element-type methods via machine learning, with applications to radiative transfer

TL;DR

This paper introduces element learning, a machine learning-based method to accelerate finite element-type PDE solvers by learning element-wise solution maps, enabling faster and more flexible solutions across various geometries and parameters.

Contribution

The paper presents a novel element learning approach that replaces local solvers in finite element methods with neural networks, significantly speeding up PDE solutions without retraining for different domains.

Findings

Achieves 5 to 10 times speed-up over classical methods.

Maintains a fixed accuracy of 10^{-3} in relative L2 error.

Applicable to radiative transfer equations with diverse scenarios.

Abstract

In this paper, we propose a systematic approach for accelerating finite element-type methods by machine learning for the numerical solution of partial differential equations (PDEs). The main idea is to use a neural network to learn the solution map of the PDEs and to do so in an element-wise fashion. This map takes input of the element geometry and the PDEs' parameters on that element, and gives output of two operators -- (1) the in2out operator for inter-element communication, and (2) the in2sol operator (Green's function) for element-wise solution recovery. A significant advantage of this approach is that, once trained, this network can be used for the numerical solution of the PDE for any domain geometry and any parameter distribution without retraining. Also, the training is significantly simpler since it is done on the element level instead on the entire domain. We call this approach element learning. This method is closely related to hybridizbale discontinuous Galerkin (HDG) methods in the sense that the local solvers of HDG are replaced by machine learning approaches. Numerical tests are presented for an example PDE, the radiative transfer equation, in a variety of scenarios with idealized or realistic cloud fields, with smooth or sharp gradient in the cloud boundary transition. Under a fixed accuracy level of $10^{-3}$ in the relative $L^2$ error, and polynomial degree $p=6$ in each element, we observe an approximately 5 to 10 times speed-up by element learning compared to a classical finite element-type method.