The automated discovery of kinetic rate models - methodological frameworks

Created by W.Langdon from gp-bibliography.bib Revision:1.8414

@Article{de-Carvalho-Servia:2024:DD,

• author = "Miguel Angel {de Carvalho Servia} and Ilya Orson Sandoval and King Kuok (Mimi) Hii and Klaus Hellgardt and Dongda Zhang and Ehecatl {Antonio del Rio Chanona}",
• title = "The automated discovery of kinetic rate models - methodological frameworks",
• journal = "Digital Discovery",
• year = "2024",
• volume = "3",
• number = "5",
• pages = "954--968",
• keywords = "genetic algorithms, genetic programming",
• ISSN = "2635-098X",
• URL = "https://www.sciencedirect.com/science/article/pii/S2635098X24000676",
• DOI = "doi:10.1039/d3dd00212h",
• abstract = "The industrialization of catalytic processes requires reliable kinetic models for their design, optimisation and control. Mechanistic models require significant domain knowledge, while data-driven and hybrid models lack interpretability. Automated knowledge discovery methods, such as ALAMO (Automated Learning of Algebraic Models for Optimisation), SINDy (Sparse Identification of Nonlinear Dynamics), and genetic programming, have gained popularity but suffer from limitations such as needing model structure assumptions, exhibiting poor scalability, and displaying sensitivity to noise. To overcome these challenges, we propose two methodological frameworks, ADoK-S and ADoK-W (Automated Discovery of Kinetic rate models using a Strong/Weak formulation of symbolic regression), for the automated generation of catalytic kinetic models using a robust criterion for model selection. We leverage genetic programming for model generation and a sequential optimisation routine for model refinement. The frameworks are tested against three case studies of increasing complexity, demonstrating their ability to retrieve the underlying kinetic rate model with limited noisy data from the catalytic systems, showcasing their potential for chemical reaction engineering applications",
• notes = "Electronic supplementary information ({ESI)} available: (1) A detailed evaluation of various model selection criteria, leading to the adoption of {AIC} for both {ADoK-S} and {ADoK-W;} (2) an analytical discussion leading to the use of the two top-performing models from {ADoK-S} or {ADoK-W} in {MBDoE}, as opposed to using Gaussian process state space models and other naive parametric models; (3) a benchmarking study comparing state-of-the-art derivative approximation methods against our {GP-based} approach; (4) the performance of {ADoK-S} on an additional multi-reaction case study.",

}

Genetic Programming entries for Miguel Angel de Carvalho Servia Ilya Orson Sandoval King Kuok (Mimi) Hii Klaus Hellgardt Dongda Zhang Ehecatl Antonio del Rio Chanona

Citations