Data-driven recursive kinetic modeling for chemical reactions

Kinetic models are crucial for analyzing reaction mechanisms and optimizing conditions. However, traditional models suffer from limitations such as lack of accuracy, narrow applicability, and difficulty in handling complex reaction conditions. Here, we develop a data-driven kinetic model with recursive algorithm and a multiple estimation strategy to predict chemical reaction kinetics. The model establishes recursive relationships between the concentrations of reactants or products at different times, rather than traditional concentration-time equations, to describe the kinetic patterns. It demonstrates superior accuracy, broad application scope, robustness, and few-shot learning capability on a simulated dataset including 18 chemical reaction types. Furthermore, its applicability to real-world chemical reactions is confirmed on the datasets of three practical reactions with complex kinetics. In addition, its advantages over traditional models were summarized through comprehensive comparison. This work introduces a high-performance kinetic model, offering a potential to accelerate chemical research via advanced kinetic analysis.