Benchmarking Physics-Informed Neural Networks and Boundary Elements Methods for Wave Scattering

2025/09/15 by Oscar Rincón-Cardeno, Rincón-Cardeno, Oscar, Gregorio Pérez Bernal +5
Earth and Planetary Sciences · Engineering · #Artificial neural network #Boundary (topology) #Boundary element method #Computation #Electromagnetic Simulation and Numerical Methods #FOS: Computer and information sciences #Helmholtz equation #Helmholtz free energy #Hyperparameter #Machine Learning (cs.LG) #Scattering #Seismic Waves and Analysis #Structural Health Monitoring Techniques

paper · pdf · doi:10.48550/arxiv.2509.12483

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/09/15 · openalex created_date 2025/10/18 · openalex updated_date 2026/08/05

Abstract

This study compares the Boundary Element Method (BEM) and Physics-Informed Neural Networks (PINNs) for solving the two-dimensional Helmholtz equation in wave scattering problems. The objective is to evaluate the performance of both methods under the same conditions. We solve the Helmholtz equation using BEM and PINNs for the same scattering problem. PINNs are trained by minimizing the residual of the governing equations and boundary conditions with their configuration determined through hyperparameter optimization, while BEM is applied using boundary discretization. Both methods are evaluated in terms of solution accuracy and computation time. We conducted numerical experiments by varying the number of boundary integration points for the BEM and the number of hidden layers and neurons per layer for the PINNs. We performed a hyperparameter tuning to identify an adequate PINN configuration for this problem as a network with 3 hidden layers and 25 neurons per layer, using a learning rate of 10^-2 and a sine activation function. At comparable levels of accuracy, the assembly and solution of the BEM system required a computational time on the order of 10^-2~s, whereas the training time of the PINN was on the order of 10²~s, corresponding to a difference of approximately four orders of magnitude. However, once trained, the PINN achieved evaluation times on the order of 10^-2~s, which is about two orders of magnitude faster than the evaluation of the BEM solution at interior points. This work establishes a procedure for comparing BEM and PINNs. It also presents a direct comparison between the two methods for the scattering problem. The analysis provides quantitative data on their performance, supporting their use in future research on wave propagation problems and outlining challenges and directions for further investigation.

Citations

• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• On the Generalization of PINNs outside the training domain and the Hyperparameters influencing it
• Can Physics-Informed Neural Networks beat the Finite Element Method?
• Hyper-parameter tuning of physics-informed neural networks: Application to Helmholtz problems
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Optuna: A Next-generation Hyperparameter Optimization Framework
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations

Related

• Taper-based scattering formulation of the Helmholtz equation to improve the training process of Physics-Informed Neural Networks
• Boundary integrated neural networks (BINNs) for acoustic radiation and scattering
• Neural network-driven domain decomposition for efficient solutions to the Helmholtz equation
• PIBNet: a Physics-Inspired Boundary Network for Multiple Scattering Simulations
• Feasibility study on solving the Helmholtz equation in 3D with PINNs