Shape Derivative-Informed Neural Operators with Application to Risk-Averse Shape Optimization

TL;DR

Shape-DINO is a neural operator framework that accelerates and improves shape optimization under uncertainty by learning PDE solutions and their derivatives, enabling reliable gradients and significant computational speedups.

Contribution

We introduce Shape-DINO, a derivative-informed neural operator that jointly learns PDE solutions and their derivatives, improving accuracy and efficiency in large-scale shape optimization under uncertainty.

Findings

Achieves 3-8 orders-of-magnitude speedup in evaluations.

Reduces PDE solves by 1-2 orders-of-magnitude for a single problem.

Produces more reliable optimization results than non-derivative-informed surrogates.

Abstract

Shape optimization under uncertainty (OUU) is computationally intensive for classical PDE-based methods due to the high cost of repeated sampling-based risk evaluation across many uncertainty realizations and varying geometries, while standard neural surrogates often fail to provide accurate and efficient sensitivities for optimization. We introduce Shape-DINO, a derivative-informed neural operator framework for learning PDE solution operators on families of varying geometries, with a particular focus on accelerating PDE-constrained shape OUU. Shape-DINOs encode geometric variability through diffeomorphic mappings to a fixed reference domain and employ a derivative-informed operator learning objective that jointly learns the PDE solution and its Fr\'echet derivatives with respect to design variables and uncertain parameters, enabling accurate state predictions and reliable gradients for large-scale OUU. We establish a priori error bounds linking surrogate accuracy to optimization error and prove universal approximation results for multi-input reduced basis neural operators in suitable $C^1$ norms. We demonstrate efficiency and scalability on three representative shape OUU problems, including boundary design for a Poisson equation and shape design governed by steady-state Navier-Stokes exterior flows in two and three dimensions. Across these examples, Shape-DINOs produce more reliable optimization results than operator surrogates trained without derivative information. In our examples, Shape-DINOs achieve 3-8 orders-of-magnitude speedups in state and gradient evaluations. Counting training data generation, Shape-DINOs reduce necessary PDE solves by 1-2 orders-of-magnitude compared to a strictly PDE-based approach for a single OUU problem. Moreover, Shape-DINO construction costs can be amortized across many objectives and risk measures, enabling large-scale shape OUU for complex systems.