Computer Vision for Kinetic Analysis of Lab- and Process-Scale Mixing Phenomena

Parallel and High Throughput Reaction Monitoring with Computer Vision

We report the development and applications of a computer vision based reaction monitoring method for parallel and high throughput experimentation (HTE). Whereas previous efforts reported methods to extract bulk kinetics of one reaction from one video, this new approach enables one video to capture bulk kinetics of multiple reactions running in parallel. Case studies, in and beyond well-plate high throughput settings, are described. Analysis of parallel dye-quenching hydroxylations, DMAP-catalysed esterification, solid-liquid sedimentation dynamics, metal catalyst degradation, and biologically-relevant sugar-mediated nitro reduction reactions have each provided insight into the scope and limitations of camera-enabled high throughput kinetics as a means of widening known analytical bottlenecks in HTE for reaction discovery, mechanistic understanding, and optimisation. It is envisaged that the nature of the multi-reaction time-resolved datasets made available by this analytical approach will later serve a broad range of downstream efforts in machine learning approaches to exploring chemical space.

A Computer Vision Approach toward Verifying CFD Models of Stirred Tank Reactors

Mixing is one of the most important nonchemical considerations in the design of scalable processes. While noninvasive imaging approaches to deliver a quantifiable understanding of mixing dynamics are well-known, the use of imaging to verify computational fluid dynamics (CFD) models remains in its infancy. Herein, we use colorimetric reactions and our kinetic imaging software, Kineticolor, to explore (i) the correlation of imaging kinetics with pH probe measurements, (ii) feed point sensitivity for Villermaux-Dushman-type competing parallel reactions, and (iii) the use of experimental imaging kinetic data to qualitatively assess CFD models. We report further evidence that the influences of the stirring rate, baffle presence, and feed position on mixing in a tank reactor can be informatively captured with a camcorder and help experimentally verify CFD models. Overall, this work advances scarce little precedent in demonstrating the use of computer vision to verify CFD models of fluid flow in tank reactors.

Keeping an "eye" on the experiment: computer vision for real-time monitoring and control

This work presents a generalizable computer vision (CV) and machine learning model that is used for automated real-time monitoring and control of a diverse array of workup processes. Our system simultaneously monitors multiple physical outputs (e.g., liquid level, homogeneity, turbidity, solid, residue, and color), offering a method for rapid data acquisition and deeper analysis from multiple visual cues. We demonstrate a single platform (consisting of CV, machine learning, real-time monitoring techniques, and flexible hardware) to monitor and control vision-based experimental techniques, including solvent exchange distillation, antisolvent crystallization, evaporative crystallization, cooling crystallization, solid-liquid mixing, and liquid-liquid extraction. Both qualitative (video capturing) and quantitative data (visual outputs measurement) were obtained which provided a method for data cross-validation. Our CV model's ease of use, generalizability, and non-invasiveness make it an appealing complementary option to in situ and real-time analytical monitoring tools and mathematical modeling. Additionally, our platform is integrated with Mettler-Toledo's iControl software, which acts as a centralized system for real-time data collection, visualization, and storage. With consistent data representation and infrastructure, we were able to efficiently transfer the technology and reproduce results between different labs. This ability to easily monitor and respond to the dynamic situational changes of the experiments is pivotal to enabling future flexible automation workflows.

Computer vision as a new paradigm for monitoring of solution and solid phase peptide synthesis

We report a strategy for the camera-enabled non-contact colourimetric reaction monitoring and optimisation of amide bond formation, mediated by coupling reagents. For amide bond formation in solution phase, investigation of reactions mediated by HATU, PyAOP, and DIC/Oxyma evidenced correlations between colour parameters extracted from video data and conversion to amide product measured by off-line HPLC analysis of concentration. These correlations, supported by mutual information analysis, were further investigated using video recordings of solid phase peptide synthesis (SPPS), co-analysed by off-line HPLC to track remaining unreacted substrate in solution. An optimisation method of coupling time in SPPS was derived from ΔE (a measurement of colour contrast), giving comparable isolated peptide yield and purity at 65-95% reduced overall reaction time. The same colour data enabled data-rich monitoring of reaction rate attenuation, consisted with computationally-derived measures of amino acid steric bulk. These findings provide a foundation for exploring the use of camera technology and computer vision towards automated and online mechanistic profiling of SPPS.

Teaching old presumptive tests new digital tricks with computer vision for forensic applications

Presumptive (or 'spot') tests have served forensic scientists, law enforcement, and legal practitioners for over a hundred years. Yet, the intended design of such tests, enabling quick identification of drugs by-eye, also hides their full potential. Here, we report the development and application of time-resolved imaging methods of reactions attending spot tests for amphetamines, barbiturates, and benzodiazepines. Analysis of the reaction videos helps distinguish drugs within the same structural class that, by-eye, are judged to give the same qualitative spot test result. It is envisaged that application of these results will bridge the existing suite of field and lab-based confirmatory forensic tests, and support a broader range of colorimetric sensing technologies.

Coaxial Dielectric Spectroscopy as an In-Line Process Analytical Technique for Reaction Monitoring

The suitability of broadband dielectric spectroscopy (DS) as a tool for in-line (in situ) reaction monitoring is demonstrated. Using the esterification of 4-nitrophenol as a test-case, we show that multivariate analysis of time-resolved DS data-collected across a wide frequency range with a coaxial dip-probe-allows reaction progress to be measured with both high precision and high accuracy. In addition to the workflows for data collection and analysis, we also establish a convenient method for rapidly assessing the applicability of DS to previously untested reactions or processes. We envisage that, given its orthogonality to other spectroscopic methods, its low cost, and its ease of implementation, DS will be a valuable addition to the process chemist's analytical toolbox.

Computer vision for non-contact monitoring of catalyst degradation and product formation kinetics

We report a computer vision strategy for the extraction and colorimetric analysis of catalyst degradation and product-formation kinetics from video footage. The degradation of palladium(ii) pre-catalyst systems to form 'Pd black' is investigated as a widely relevant case study for catalysis and materials chemistries. Beyond the study of catalysts in isolation, investigation of Pd-catalyzed Miyaura borylation reactions revealed informative correlations between colour parameters (most notably ΔE, a colour-agnostic measure of contrast change) and the concentration of product measured by off-line analysis (NMR and LC-MS). The breakdown of such correlations helped inform conditions under which reaction vessels were compromised by air ingress. These findings present opportunities to expand the toolbox of non-invasive analytical techniques, operationally cheaper and simpler to implement than common spectroscopic methods. The approach introduces the capability of analyzing the macroscopic 'bulk' for the study of reaction kinetics in complex mixtures, in complement to the more common study of microscopic and molecular specifics.

Determining Phase Separation Dynamics with an Automated Image Processing Algorithm

The problems of extracting products efficiently from reaction workups are often overlooked. Issues such as emulsions and rag layer formation can cause long separation times and slow production, thus resulting in manufacturing inefficiencies. To better understand science within this area and to support process development, an image processing methodology has been developed that can automatically track the interface between liquid-liquid phases and provide a quantitative measure of the separation rate of two immiscible liquids. The algorithm is automated and has been successfully applied to 29 cases. Its robustness has been demonstrated with a variety of different liquid mixtures that exhibit a wide range of separation behavior-making such an algorithm suited to high-throughput experimentation. The information gathered from applying the algorithm shows how issues resulting from poor separations can be detected early in process development.