Physics-Informed Uncertainty Enables Reliable AI-driven Design

TL;DR

This paper introduces physics-informed uncertainty as a computationally efficient way to improve AI-driven inverse design, significantly increasing success rates and reducing costs in designing frequency-selective surfaces.

Contribution

It presents a novel physics-informed uncertainty method integrated into a multi-fidelity optimization workflow for inverse design, outperforming traditional surrogate models.

Findings

Success rate increased from <10% to >50%.

Computational cost reduced by an order of magnitude.

Physics-informed uncertainty effectively guides high-dimensional design optimization.

Abstract

Inverse design is a central goal in much of science and engineering, including frequency-selective surfaces (FSS) that are critical to microelectronics for telecommunications and optical metamaterials. Traditional surrogate-assisted optimization methods using deep learning can accelerate the design process but do not usually incorporate uncertainty quantification, leading to poorer optimization performance due to erroneous predictions in data-sparse regions. Here, we introduce and validate a fundamentally different paradigm of Physics-Informed Uncertainty, where the degree to which a model's prediction violates fundamental physical laws serves as a computationally-cheap and effective proxy for predictive uncertainty. By integrating physics-informed uncertainty into a multi-fidelity uncertainty-aware optimization workflow to design complex frequency-selective surfaces within the 20 - 30 GHz range, we increase the success rate of finding performant solutions from less than 10% to over 50%, while simultaneously reducing computational cost by an order of magnitude compared to the sole use of a high-fidelity solver. These results highlight the necessity of incorporating uncertainty quantification in machine-learning-driven inverse design for high-dimensional problems, and establish physics-informed uncertainty as a viable alternative to quantifying uncertainty in surrogate models for physical systems, thereby setting the stage for autonomous scientific discovery systems that can efficiently and robustly explore and evaluate candidate designs.