Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions

TL;DR

This paper introduces Cut-DeepONet, a novel two-stage training framework that explicitly models discontinuities in PDE solutions by partitioning the domain, improving accuracy and efficiency over existing methods.

Contribution

The paper proposes a new lifting strategy and a domain partitioning approach to better handle discontinuities in neural operator learning, reducing model complexity and data requirements.

Findings

Outperforms state-of-the-art methods on benchmark PDEs

Requires fewer trainable parameters and low-resolution data

Effectively captures discontinuities and sharp transitions

Abstract

Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently continuous representations struggle to capture discontinuities and sharp transitions. Existing approaches typically approximate such features within continuous function spaces, often requiring increased model capacity and high-resolution data. In this work, we propose Cut-DeepONet, a two-stage training framework that explicitly models discontinuities while reducing learning complexity. Our approach reformulates the problem via a lifting strategy, partitioning the domain into smooth subregions while representing discontinuities as boundaries in a higher-dimensional space. This separation aligns the operator learning task with the inductive bias of neural networks and avoids directly approximating discontinuities. An additional network predicts input-dependent discontinuity locations for unseen inputs, which are then used to guide the neural operator in generating smooth components within each region. Experiments on benchmark PDEs show that Cut-DeepONet outperforms state-of-the-art methods, even when trained on low-resolution datasets. The method excels on problems with discontinuities and sharp transitions, while using fewer trainable parameters. Our results highlight the benefits of changing the representation of operator learning rather than increasing model complexity.