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

TL;DR

This paper introduces PI-ADoK, a physics-informed symbolic regression framework that efficiently discovers kinetic models with physical constraints, reducing experimental effort and improving model reliability in catalytic process design.

Contribution

The novel PI-ADoK framework integrates physical constraints into symbolic regression and employs uncertainty quantification, advancing data-efficient and physically consistent kinetic model discovery.

Findings

Reduces experimental requirements for model convergence

Improves model fidelity compared to traditional methods

Provides credible prediction intervals through uncertainty quantification

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.