Uncertainty-Aware Data-Based Method for Fast and Reliable Shape Optimization

2026-01-29

AI Summary

This work addresses the high prediction errors and resulting unreliability of data-driven shape optimization when applied to out-of-distribution samples. To mitigate this issue, the authors propose an Uncertainty-Aware Data-Driven Optimization framework (UA-DBO), which explicitly incorporates the uncertainty quantified from surrogate model predictions into the aerodynamic objective function for the first time. Leveraging a probabilistic encoder-decoder architecture, UA-DBO estimates predictive uncertainty and employs a confidence-aware objective function to automatically avoid regions of high uncertainty. Evaluated on airfoil optimization tasks involving drag divergence and buffet performance, UA-DBO significantly reduces prediction errors, outperforms conventional data-driven approaches, and achieves performance comparable to full high-fidelity simulation-based optimization while offering substantial computational acceleration.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Data-based optimization (DBO) offers a promising approach for efficiently optimizing shape for better aerodynamic performance by leveraging a pretrained surrogate model for offline evaluations during iterations. However, DBO heavily relies on the quality of the training database. Samples outside the training distribution encountered during optimization can lead to significant prediction errors, potentially misleading the optimization process. Therefore, incorporating uncertainty quantification into optimization is critical for detecting outliers and enhancing robustness. This study proposes an uncertainty-aware data-based optimization (UA-DBO) framework to monitor and minimize surrogate model uncertainty during DBO. A probabilistic encoder-decoder surrogate model is developed to predict uncertainties associated with its outputs, and these uncertainties are integrated into a model-confidence-aware objective function to penalize samples with large prediction errors during data-based optimization process. The UA-DBO framework is evaluated on two multipoint optimization problems aimed at improving airfoil drag divergence and buffet performance. Results demonstrate that UA-DBO consistently reduces prediction errors in optimized samples and achieves superior performance gains compared to original DBO. Moreover, compared to multipoint optimization based on full computational simulations, UA-DBO offers comparable optimization effectiveness while significantly accelerating optimization speed.

Problem

• uncertainty quantification
• data-based optimization
• surrogate model
• shape optimization
• out-of-distribution samples

Innovation

• uncertainty-aware optimization
• data-based optimization
• probabilistic surrogate model
• aerodynamic shape optimization
• model confidence