Cheap2Rich: A Multi-Fidelity Framework for Data Assimilation and System Identification of Multiscale Physics -- Rotating Detonation Engines

2026-01-28

AI Summary

This work addresses the sim-to-real gap in modeling strongly multiscale systems—such as rotating detonation engines—where computationally inexpensive models fail to reproduce high-fidelity states. To bridge this gap, the authors propose the Cheap2Rich framework, which integrates low-fidelity physical priors with an interpretable, learning-based bias correction to reconstruct high-dimensional state spaces from sparse sensor data. This approach introduces, for the first time, an interpretable multifidelity bias modeling strategy tailored to such systems, enabling not only accurate reconstruction of high-fidelity dynamics but also explicit separation of injector-driven bias dynamics with clear physical meaning. Experimental results demonstrate that the framework achieves efficient and interpretable state reconstruction and system identification for multiscale systems, thereby establishing a foundation for real-time monitoring and control.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Bridging the sim2real gap between computationally inexpensive models and complex physical systems remains a central challenge in machine learning applications to engineering problems, particularly in multi-scale settings where reduced-order models typically capture only dominant dynamics. In this work, we present Cheap2Rich, a multi-scale data assimilation framework that reconstructs high-fidelity state spaces from sparse sensor histories by combining a fast low-fidelity prior with learned, interpretable discrepancy corrections. We demonstrate the performance on rotating detonation engines (RDEs), a challenging class of systems that couple detonation-front propagation with injector-driven unsteadiness, mixing, and stiff chemistry across disparate scales. Our approach successfully reconstructs high-fidelity RDE states from sparse measurements while isolating physically meaningful discrepancy dynamics associated with injector-driven effects. The results highlight a general multi-fidelity framework for data assimilation and system identification in complex multi-scale systems, enabling rapid design exploration and real-time monitoring and control while providing interpretable discrepancy dynamics. Code for this project is is available at: github.com/kro0l1k/Cheap2Rich.

Problem

• sim2real gap
• multi-fidelity
• data assimilation
• system identification
• multiscale physics

Innovation

• multi-fidelity
• data assimilation
• system identification
• interpretable discrepancy
• rotating detonation engine