Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics
2026-06-01 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a hybrid modeling approach that combines known chemical rules with a small learned part to better predict how polymers form during a reaction. Instead of learning everything from scratch, their model uses known equations and only learns uncertain parts from limited data, making it more efficient. They tested this on a specific polymer reaction and found their method predicted outcomes more accurately and sensibly than fully data-driven models, even with very few and noisy measurements. This shows that blending mechanistic knowledge with smart learning can improve predictions when data is scarce.
polymerizationNeural Ordinary Differential Equation (NODE)free-radical polymerizationmethyl methacrylate (MMA)mechanistic modelingdata-driven modelingbatch polymerizationmass balancesmodel parameterizationroot mean square error (RMSE)
Authors
Marah Almanasreh, Alexander Mitsos, Eike Cramer
Abstract
Accurate prediction of polymerization dynamics is essential for process design, control, and optimization. Yet, purely mechanistic models require labor-intensive parameterization of partially characterized kinetics, while purely data-driven models demand large, diverse datasets that are costly to obtain, particularly in early-design stages. We propose a hybrid Neural Ordinary Differential Equation (NODE) framework for data-efficient modeling of free-radical polymerization. Using batch polymerization of methyl methacrylate (MMA) as a case study, the mechanistic mass balances are retained explicitly, and only the partially-characterized effective radical concentration governing monomer consumption is learned from data through a neural network surrogate, while established reactions such as initiator decomposition, propagation, and termination remain physically modeled. The hybrid NODE is evaluated against a discrete-time feedforward neural network and a purely data-driven NODE under sparse data conditions, with models trained on as few as ten measurements under both regular and irregular sampling. The hybrid NODE consistently achieves lower prediction errors and more physically consistent extrapolations than both purely data-driven baselines. In a generalization scenario with noisy data and unseen operating conditions, the hybrid NODE achieves an RMSE of 0.013, compared to 0.31 for the data-driven NODE and 0.68 for the discrete-time model, demonstrating that learning only a closure term rather than the full dynamics is sufficient for reliable prediction under limited data availability.