Constraint-Guided Symbolic Regression for Data-Efficient Kinetic Model Discovery

2025-07-03

AI Summary

Catalytic kinetic modeling faces two key challenges: mechanistic models rely heavily on expert knowledge, while data-driven approaches lack physical interpretability and consistency. To address these, we propose PI-ADoK—a physics-informed symbolic regression framework that embeds prior physical laws (e.g., conservation principles and thermodynamic constraints) directly into the symbolic search process, thereby substantially narrowing the hypothesis space. Furthermore, PI-ADoK incorporates Metropolis–Hastings sampling to jointly quantify structural and parametric uncertainty. Evaluated across multiple catalytic reaction systems, PI-ADoK yields models that are both highly interpretable and physically consistent. It improves prediction accuracy by 12–28%, reduces experimental data requirements by 35–50%, accelerates convergence by 2.1–3.6×, and delivers calibrated, reliability-controllable prediction intervals.

Technology Category

• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

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

Abstract

The industrialization of catalytic processes hinges on the availability of reliable kinetic models for design, optimization, and control. Traditional mechanistic models demand extensive domain expertise, while many data-driven approaches often lack interpretability and fail to enforce physical consistency. To overcome these limitations, we propose the Physics-Informed Automated Discovery of Kinetics (PI-ADoK) framework. By integrating physical constraints directly into a symbolic regression approach, PI-ADoK narrows the search space and substantially reduces the number of experiments required for model convergence. Additionally, the framework incorporates a robust uncertainty quantification strategy via the Metropolis-Hastings algorithm, which propagates parameter uncertainty to yield credible prediction intervals. Benchmarking our method against conventional approaches across several catalytic case studies demonstrates that PI-ADoK not only enhances model fidelity but also lowers the experimental burden, highlighting its potential for efficient and reliable kinetic model discovery in chemical reaction engineering.

Problem

• Develops kinetic models for catalytic process industrialization
• Enhances interpretability and physical consistency in data-driven models
• Reduces experimental burden with physics-informed symbolic regression

Innovation

• Physics-informed symbolic regression for kinetic models
• Metropolis-Hastings uncertainty quantification strategy
• Constraint-guided approach reduces experimental burden