Optimizing telescoped heterogeneous catalysis with noise-resilient multi-objective Bayesian optimization

Luo, Guihua; Yang, Xilin; Su, Weike; Qi, Tingting; Xu, Qilin; Su, An

doi:10.26434/chemrxiv-2024-9257k

Cited by 2 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This iteration of obtaining experimental values, updating the GP model, and recommending new parameter values continues until a predetermined number of experiments is reached. The optimization was conducted on the FlowBO framework developed in our previous work. , …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Continuous Flow Synthesis of N,O-Dimethyl-N′-nitroisourea Monitored by Inline Fourier Transform Infrared Spectroscopy: Bayesian Optimization and Kinetic Modeling

Guo,

Luo,

Chai

et al. 2024

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

The synthesis of N,O-dimethyl-N′-nitroisourea, crucial intermediates in pesticide manufacturing, was explored through a substitution reaction between O-methyl-N-nitroisourea and methylamine within a novel continuous flow microreactor system, featuring Fourier transform infrared (FTIR) in-line analysis for real-time monitoring. In this paper, the reaction is investigated using two optimization methods: the contemporary machine learning-based Bayesian optimization and the traditional kinetic modeling. Remarkably, both strategies obtained a similar yield of approximately 83% under equivalent reaction parametersspecifically, an initial reactant concentration of 0.2 mol/L, a reaction temperature of 40 °C, a molar ratio of reactants at 5:1, and a residence time of 240 min. The Bayesian optimization method demonstrated a notable efficiency, achieving optimal conditions within a mere 20 experiments, in contrast to the kinetic modeling approach, which required a more laborious effort for model formulation and validation. However, kinetic modeling allows for a more comprehensive understanding of the reaction, and the two optimization methods fully demonstrate their respective strengths and weaknesses. This study not only highlights the potential of integrating advanced machine learning methods into chemical process optimization but also sets the stage for further exploration into efficient, data-driven approaches in chemical synthesis.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The optimization was conducted on the FlowBO framework developed in our previous work. 28,49 2.6. Kinetic Modeling Optimization Process.…”

Section: Bayesian Optimization Workflowmentioning

confidence: 99%

Continuous Flow Synthesis of N,O-Dimethyl-N′-nitroisourea Monitored by Inline Fourier Transform Infrared Spectroscopy: Bayesian Optimization and Kinetic Modeling

Guo,

Luo,

Chai

et al. 2024

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…CHIMERA is an algorithm that considers multiobjective optimization with a priori user-defined objective hierarchy and tolerances. Further discussions on the choice of acquisition functions for especially noisy systems can be found in the work of Luo et al (2024) …”

Section: Data-driven Exploitationmentioning

confidence: 99%

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

Benavides-Hernández,

Dumeignil

2024

ACS Catal.

View full text Add to dashboard Cite

This review paper delves into synergistic integration of artificial intelligence (AI) and machine learning (ML) with highthroughput experimentation (HTE) in the field of heterogeneous catalysis, presenting a broad spectrum of contemporary methodologies and innovations. We methodically segmented the text into three core areas: catalyst characterization, data-driven exploitation, and data-driven discovery. In the catalyst characterization part, we outline current and prospective techniques used for HTE and how AI-driven strategies can streamline or automate their analysis. The data-driven exploitation part is divided into themes, strategies, and techniques that offer flexibility for either modular application or creation of customized solutions. In the data-driven exploration part we present applications that enable exploration of areas outside the experimentally tested chemical space, incorporating a section on computational methods for identifying new prospects. The review concludes by addressing the current limitations within the field and suggesting possible avenues for future research.

show abstract

Optimizing telescoped heterogeneous catalysis with noise-resilient multi-objective Bayesian optimization

Cited by 2 publications

References 26 publications

Continuous Flow Synthesis of N,O-Dimethyl-N′-nitroisourea Monitored by Inline Fourier Transform Infrared Spectroscopy: Bayesian Optimization and Kinetic Modeling

Continuous Flow Synthesis of N,O-Dimethyl-N′-nitroisourea Monitored by Inline Fourier Transform Infrared Spectroscopy: Bayesian Optimization and Kinetic Modeling

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

Contact Info

Product

Resources

About