Hybrid Physics-Data Enrichments to Represent Uncertainty in Reduced Gas-Surface Chemistry Models for Hypersonic Flight

2025-09-09

AI Summary

In hypersonic re-entry, ablative thermal protection system (TPS) performance prediction relies on gas–surface chemical models; however, computationally tractable low-fidelity models often omit key species and reactions, leading to large errors—particularly in critical product predictions such as CO—and hindering rigorous uncertainty quantification. To address this, we propose a physics-guided, data-driven hybrid enhancement method: only three physically interpretable supplemental surface reactions are introduced into the low-fidelity model, coupled with a bias-correction and uncertainty-quantification module. The approach integrates finite-rate surface chemistry, model order reduction, and data-driven compensation, preserving computational efficiency while substantially improving CO production prediction accuracy. Numerical experiments demonstrate over 70% error reduction compared to baseline low-fidelity models. This framework establishes a new paradigm for TPS assessment—one that balances reliability, physical interpretability, and practical deployability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

During hypersonic flight, air reacts with a planetary re-entry vehicle's thermal protection system (TPS), creating reaction products that deplete the TPS. Reliable assessment of TPS performance depends on accurate ablation models. New finite-rate gas-surface chemistry models are advancing state-of-the-art in TPS ablation modeling, but model reductions that omit chemical species and reactions may be necessary in some cases for computational tractability. This work develops hybrid physics-based and data-driven enrichments to improve the predictive capability and quantify uncertainties in such low-fidelity models while maintaining computational tractability. We focus on discrepancies in predicted carbon monoxide production that arise because the low-fidelity model tracks only a subset of reactions. To address this, we embed targeted enrichments into the low-fidelity model to capture the influence of omitted reactions. Numerical results show that the hybrid enrichments significantly improve predictive accuracy while requiring the addition of only three reactions.

Problem

• Improving predictive capability of reduced gas-surface chemistry models
• Quantifying uncertainties in low-fidelity hypersonic ablation models
• Addressing carbon monoxide production discrepancies in simplified reaction sets

Innovation

• Hybrid physics-data enrichments for uncertainty
• Targeted enrichments capture omitted reactions influence
• Adds only three reactions for accuracy