Physics-Informed Uncertainty Enables Reliable AI-driven Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Tingkai, Ooi, Chin Chun, Jiang, Yang, Duong, Luu Trung Pham, Chiu, Pao-Hsiung, Zhao, Weijiang, Raghavan, Nagarajan, Dao, My Ha
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911399526006784
author Xue, Tingkai
Ooi, Chin Chun
Jiang, Yang
Duong, Luu Trung Pham
Chiu, Pao-Hsiung
Zhao, Weijiang
Raghavan, Nagarajan
Dao, My Ha
author_facet Xue, Tingkai
Ooi, Chin Chun
Jiang, Yang
Duong, Luu Trung Pham
Chiu, Pao-Hsiung
Zhao, Weijiang
Raghavan, Nagarajan
Dao, My Ha
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18638
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physics-Informed Uncertainty Enables Reliable AI-driven Design
Xue, Tingkai
Ooi, Chin Chun
Jiang, Yang
Duong, Luu Trung Pham
Chiu, Pao-Hsiung
Zhao, Weijiang
Raghavan, Nagarajan
Dao, My Ha
Machine Learning
Computational Physics
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.
title Physics-Informed Uncertainty Enables Reliable AI-driven Design
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2601.18638