Automated self-optimisation of multi-step reaction and separation processes using machine learning

Clayton, Adam D.; Schweidtmann, Artur M.; Clemens, Graeme; Manson, Jamie A.; Taylor, Connor J.; Niño, Carlos González; Chamberlain, Thomas W.; Kapur, Nikil; Blacker, A. John; Lapkin, Alexei A.; Bourne, Richard A.

doi:10.1016/j.cej.2019.123340

Cited by 124 publications

(95 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example of an algorithm for efficient multi-objective reaction optimization is the open-source Thompson Sampling Efficient Multi-Objective (TS-EMO). [7] Lapkin and co-workers [6,[8][9][10] have demonstrated the quality of the generated Pareto fronts, as well as the algorithm's efficiency at identifying them, when compared with alternative algorithms such as ParEGO. [11] Alternative examples multi-objective algorithms [12] developed for chemical process include Phoenics [13] and Chimera.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning‐Enabled Autonomous Flow Chemistry Platform for Process Optimization of Multiple Reaction Metrics

2020

Self Cite

View full text Add to dashboard Cite

Self-optimization of chemical reactions using machine learning multi-objective algorithms has the potential to significantly shorten overall process development time, providing users with valuable information about economic and environmental factors. Using the Thompson Sampling Efficient Multi-Objective (TS-EMO) algorithm, the self-optimization flow chemistry system in this report demonstrates the ability to identify optimum reaction conditions and trade-offs (Pareto fronts) between conflicting optimization objectives, such as yield, cost, spacetime yield, and E-factor, in a data efficient manner. Advantageously, the robust system consists of exclusively commercially available equipment and a user-friendly MATLAB graphical user interface, and was shown to autonomously run 131 experiments over 69 hours uninterrupted.

show abstract

Section: Introductionmentioning

confidence: 99%

A Machine Learning‐Enabled Autonomous Flow Chemistry Platform for Process Optimization of Multiple Reaction Metrics

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of design‐of‐experiment (DoE) methods partially addresses these drawbacks, but the high number of experiments required to locate a satisfactory optimum associated to the absence of feedback are strong handicaps to develop efficient automations. The development and optimization of continuous flow processes can be greatly speeded‐up with the use of autonomous self‐optimizing flow reactors [11–26] . These powerful automated devices combine flow reactors with process control instrumentations, in‐line/online analyses and optimization algorithms to assist the decision‐making process of chemists [27–34] .…”

Section: Resultsmentioning

confidence: 99%

Direct C−H Arylation of Indole‐3‐Acetic Acid Derivatives Enabled by an Autonomous Self‐Optimizing Flow Reactor

et al. 2020

View full text Add to dashboard Cite

Described herein is a continuous‐flow strategy for the palladium‐catalyzed direct C−H arylation of indole‐3‐acetic acid derivatives with arenediazonium salts. A fully autonomous self‐optimizing flow platform was used to efficiently optimize the coupling reaction in a three‐dimensional space. The flow methodology developed is experimentally simple, mild, broad in scope, and safer than traditional batch approaches. Our continuous‐flow approach is particularly convenient to prepare precursors of pharmaceutically relevant compounds.

show abstract

“…Another option is to use an optimization algorithm [ 5 ] in combination with a continuous‐flow platform for the automated optimization of a specific chemical transformation, which can then be expanded to expand the substrate scope. [ 6 ] Machine learning (ML) can also be used here to aid in the synthesis of small organic molecules, [ 7 ] for example, by automating the self‐optimization of chemical reactions, [ 8 ] including those that involve multiple steps, [ 9 ] and searching for new chemical reactivity. [ 10 ]…”

Section: Steps To Materials Discoverymentioning

confidence: 99%

Integrating Computational and Experimental Workflows for Accelerated Organic Materials Discovery

Greenaway

Jelfs

2021

Advanced Materials

View full text Add to dashboard Cite

Organic materials find application in a range of areas, including optoelectronics, sensing, encapsulation, molecular separations, and photocatalysis. The discovery of materials is frustratingly slow however, particularly when contrasted to the vast chemical space of possibilities based on the near limitless options for organic molecular precursors. The difficulty in predicting the material assembly, and consequent properties, of any molecule is another significant roadblock to targeted materials design. There has been significant progress in the development of computational approaches to screen large numbers of materials, for both their structure and properties, helping guide synthetic researchers toward promising materials. In particular, artificial intelligence techniques have the potential to make significant impact in many elements of the discovery process. Alongside this, automation and robotics are increasing the scale and speed with which materials synthesis can be realized. Herein, the focus is on demonstrating the power of integrating computational and experimental materials discovery programmes, including both a summary of key situations where approaches can be combined and a series of case studies that demonstrate recent successes.

show abstract

Automated self-optimisation of multi-step reaction and separation processes using machine learning

Cited by 124 publications

References 40 publications

A Machine Learning‐Enabled Autonomous Flow Chemistry Platform for Process Optimization of Multiple Reaction Metrics

A Machine Learning‐Enabled Autonomous Flow Chemistry Platform for Process Optimization of Multiple Reaction Metrics

Direct C−H Arylation of Indole‐3‐Acetic Acid Derivatives Enabled by an Autonomous Self‐Optimizing Flow Reactor

Integrating Computational and Experimental Workflows for Accelerated Organic Materials Discovery

Contact Info

Product

Resources

About