Kolmogorov-Arnold Chemical Reaction Neural Networks for learning pressure-dependent kinetic rate laws

2025-11-10

AI Summary

Traditional chemical reaction neural networks (CRNNs) struggle to model pressure-dependent reaction kinetics, limiting their applicability in complex systems such as combustion. To address this, we introduce, for the first time, the Kolmogorov–Arnold representation theorem into reaction kinetics modeling, proposing the KA-CRNN framework. This approach employs Kolmogorov–Arnold activation functions to explicitly decouple pressure and temperature dependencies of rate constants, while strictly preserving the physical constraints of the Arrhenius law and mass-action kinetics. Unlike conventional empirical or interpolation-based models, KA-CRNN enables data-driven, assumption-free learning of pressure effects. Validated on the CH₃ recombination reaction, it achieves significantly higher accuracy across wide temperature and pressure ranges. Moreover, it yields physically interpretable, parametric representations of pressure dependence. Our work establishes a new paradigm for physics-guided deep learning in complex reaction systems—bridging mechanistic understanding with flexible, data-adaptive modeling.

Technology Category

• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Chemical Reaction Neural Networks (CRNNs) have emerged as an interpretable machine learning framework for discovering reaction kinetics directly from data, while strictly adhering to the Arrhenius and mass action laws. However, standard CRNNs cannot represent pressure-dependent rate behavior, which is critical in many combustion and chemical systems and typically requires empirical formulations such as Troe or PLOG. Here, we develop Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs) that generalize CRNNs by modeling each kinetic parameter as a learnable function of system pressure using Kolmogorov-Arnold activations. This structure maintains full interpretability and physical consistency while enabling assumption-free inference of pressure effects directly from data. A proof-of-concept study on the CH3 recombination reaction demonstrates that KA-CRNNs accurately reproduce pressure-dependent kinetics across a range of temperatures and pressures, outperforming conventional interpolative models. The framework establishes a foundation for data-driven discovery of extended kinetic behaviors in complex reacting systems, advancing interpretable and physics-consistent approaches for chemical model inference.

Problem

• Extending Chemical Reaction Neural Networks to handle pressure-dependent kinetics
• Modeling kinetic parameters as learnable functions of system pressure
• Enabling assumption-free inference of pressure effects from reaction data

Innovation

• KA-CRNNs use Kolmogorov-Arnold activations for pressure functions
• Model kinetic parameters as learnable pressure-dependent functions
• Maintain interpretability while inferring pressure effects from data