Learning the Helmholtz equation operator with DeepONet for non-parametric 2D geometries
Rodolphe Barlogis, Ferhat Tamssaouet, Quentin Falcoz, Stéphane Grieu
TLDR
This paper uses DeepONet to learn the Helmholtz equation operator for 2D non-parametric geometries, linking scatterer shape to the scattered field.
Key contributions
- Develops a DeepONet to learn the Helmholtz operator for arbitrary 2D scatterer geometries.
- Encodes non-parametric shapes using signed distance functions as DeepONet input.
- Offers a computationally lighter surrogate model, avoiding FEM remeshing and training data.
- Demonstrates strong generalization to unseen geometries and supports incremental refinement.
Why it matters
This work provides a novel, efficient method for solving the Helmholtz equation on complex, non-parametric domains. It significantly reduces computational overhead by eliminating the need for remeshing and extensive FEM simulations, advancing neural operator applications in physics.
Original Abstract
This paper deals with solving the 2D Helmholtz equation on non-parametric domains, leveraging a physics-informed neural operator network based on the DeepONet framework. We consider a 2D square domain with an inclusion of arbitrary boundary geometry at its center. This inclusion acts as a scatterer for an incoming harmonic wave. The aim is to learn the operator linking the geometry of the scatterer to the resulting scattered field. A signed distance function to the boundary of the inner inclusion, evaluated at several points in the domain, is used to encode its geometry. It serves as input for the branch part of the DeepONet architecture, while local information is used as input for the trunk part. This approach enables the encoding of arbitrary geometries, whether they are parameterized or not. The evaluation of the model on unseen geometries is compared with its finite element method (FEM) equivalent to test its generalization capabilities. The trained network weights implicitly embed the local physics and their interaction with the domain geometry. If the training space sufficiently covers the target evaluation space, the model can generalize accordingly. Furthermore, it can be refined to extend to another region of interest without retraining from scratch. This framework also avoids the need to remesh the domain for each geometry. The proposed approach delivers a computationally lighter surrogate model than FEM alternatives and avoids relying on FEM-generated training data.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.