SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design

TL;DR

This paper introduces SmOOD, a smoothness-based out-of-distribution detection method that enhances the reliability of neural network surrogates in aircraft design optimization by effectively identifying OOD samples and reducing computational costs.

Contribution

The paper proposes a novel OOD detection approach, SmOOD, that leverages smoothness properties of high-fidelity simulations to improve surrogate model trustworthiness in aircraft design.

Findings

FNN surrogates outperform Gaussian Processes in predictive accuracy.

SmOOD detects approximately 85% of actual OOD samples.

Using SmOOD with FNN surrogates reduces error rate by 34.65% and speeds up computations by 58.36 times.

Abstract

Aircraft industry is constantly striving for more efficient design optimization methods in terms of human efforts, computation time, and resource consumption. Hybrid surrogate optimization maintains high results quality while providing rapid design assessments when both the surrogate model and the switch mechanism for eventually transitioning to the HF model are calibrated properly. Feedforward neural networks (FNNs) can capture highly nonlinear input-output mappings, yielding efficient surrogates for aircraft performance factors. However, FNNs often fail to generalize over the out-of-distribution (OOD) samples, which hinders their adoption in critical aircraft design optimization. Through SmOOD, our smoothness-based out-of-distribution detection approach, we propose to codesign a model-dependent OOD indicator with the optimized FNN surrogate, to produce a trustworthy surrogate model with selective but credible predictions. Unlike conventional uncertainty-grounded methods, SmOOD exploits inherent smoothness properties of the HF simulations to effectively expose OODs through revealing their suspicious sensitivities, thereby avoiding over-confident uncertainty estimates on OOD samples. By using SmOOD, only high-risk OOD inputs are forwarded to the HF model for re-evaluation, leading to more accurate results at a low overhead cost. Three aircraft performance models are investigated. Results show that FNN-based surrogates outperform their Gaussian Process counterparts in terms of predictive performance. Moreover, SmOOD does cover averagely 85% of actual OODs on all the study cases. When SmOOD plus FNN surrogates are deployed in hybrid surrogate optimization settings, they result in a decrease error rate of 34.65% and a computational speed up rate of 58.36 times, respectively.