Accelerated AI development for autonomous materials synthesis in flow

Self-Driving Laboratories for Chemistry and Materials Science

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with autonomous experimental planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.

Autonomous nanomanufacturing of lead-free metal halide perovskite nanocrystals using a self-driving fluidic lab

Lead-based metal halide perovskite (MHP) nanocrystals (NCs) have emerged as a promising class of semiconducting nanomaterials for a wide range of optoelectronic and photoelectronic applications. However, the intrinsic lead toxicity of MHP NCs has significantly hampered their large-scale device applications. Copper-base MHP NCs with composition-tunable optical properties have emerged as a prominent lead-free MHP NC candidate. However, comprehensive synthesis space exploration, development, and synthesis science studies of copper-based MHP NCs have been limited by the manual nature of flask-based synthesis and characterization methods. In this study, we present an autonomous approach for the development of lead-free MHP NCs via seamless integration of a modular microfluidic platform with machine learning-assisted NC synthesis modeling and experiment selection to establish a self-driving fluidic lab for accelerated NC synthesis science studies. For the first time, a successful and reproducible in-flow synthesis of Cs3Cu2I5 NCs is presented. Autonomous experimentation is then employed for rapid in-flow synthesis science studies of Cs3Cu2I5 NCs. The autonomously generated experimental NC synthesis dataset is then utilized for fast-tracked synthetic route optimization of high-performing Cs3Cu2I5 NCs.

Explainability and human intervention in autonomous scanning probe microscopy

The broad adoption of machine learning (ML)-based autonomous experiments (AEs) in material characterization and synthesis requires strategies development for understanding and intervention in the experimental workflow. Here, we introduce and realize a post-experimental analysis strategy for deep kernel learning-based autonomous scanning probe microscopy. This approach yields real-time and post-experimental indicators for the progression of an active learning process interacting with an experimental system. We further illustrate how this approach can be applied to human-in-the-loop AEs, where human operators make high-level decisions at high latencies setting the policies for AEs, and the ML algorithm performs low-level, fast decisions. The proposed approach is universal and can be extended to other techniques and applications such as combinatorial library analysis.

Using Data-Driven Learning to Predict and Control the Outcomes of Inorganic Materials Synthesis

The design of inorganic materials for various applications critically depends on our ability to manipulate their synthesis in a rational, robust, and controllable fashion. Different from the conventional trial-and-error approach, data-driven techniques such as the design of experiments (DoE) and machine learning are an effective and more efficient way to predictably control materials synthesis. Here, we present a Viewpoint on recent progress in leveraging such techniques for predicting and controlling the outcomes of inorganic materials synthesis. We first compare how the design choice (statistical DoE vs machine learning) affects the type of control it can offer over the resulting product attributes, information elucidated, and experimental cost. These attributes are supported by discussing select case studies from the recent literature that highlight the power of these techniques for materials synthesis. The influence of experimental bias is next discussed, followed finally by our perspectives on the major challenges in the widespread implementation of predictable and controllable materials synthesis using data-driven techniques.

A Brief Introduction to Chemical Reaction Optimization

From the start of a synthetic chemist's training, experiments are conducted based on recipes from textbooks and manuscripts that achieve clean reaction outcomes, allowing the scientist to develop practical skills and some chemical intuition. This procedure is often kept long into a researcher's career, as new recipes are developed based on similar reaction protocols, and intuition-guided deviations are conducted through learning from failed experiments. However, when attempting to understand chemical systems of interest, it has been shown that model-based, algorithm-based, and miniaturized high-throughput techniques outperform human chemical intuition and achieve reaction optimization in a much more time- and material-efficient manner; this is covered in detail in this paper. As many synthetic chemists are not exposed to these techniques in undergraduate teaching, this leads to a disproportionate number of scientists that wish to optimize their reactions but are unable to use these methodologies or are simply unaware of their existence. This review highlights the basics, and the cutting-edge, of modern chemical reaction optimization as well as its relation to process scale-up and can thereby serve as a reference for inspired scientists for each of these techniques, detailing several of their respective applications.

AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning

Closed-loop, autonomous experimentation enables accelerated and material-efficient exploration of large reaction spaces without the need for user intervention. However, autonomous exploration of advanced materials with complex, multi-step processes and data sparse environments remains a challenge. In this work, we present AlphaFlow, a self-driven fluidic lab capable of autonomous discovery of complex multi-step chemistries. AlphaFlow uses reinforcement learning integrated with a modular microdroplet reactor capable of performing reaction steps with variable sequence, phase separation, washing, and continuous in-situ spectral monitoring. To demonstrate the power of reinforcement learning toward high dimensionality multi-step chemistries, we use AlphaFlow to discover and optimize synthetic routes for shell-growth of core-shell semiconductor nanoparticles, inspired by colloidal atomic layer deposition (cALD). Without prior knowledge of conventional cALD parameters, AlphaFlow successfully identified and optimized a novel multi-step reaction route, with up to 40 parameters, that outperformed conventional sequences. Through this work, we demonstrate the capabilities of closed-loop, reinforcement learning-guided systems in exploring and solving challenges in multi-step nanoparticle syntheses, while relying solely on in-house generated data from a miniaturized microfluidic platform. Further application of AlphaFlow in multi-step chemistries beyond cALD can lead to accelerated fundamental knowledge generation as well as synthetic route discoveries and optimization.

Non-fouling flow reactors for nanomaterial synthesis

This review provides a holistic description of flow reactor fouling for wet-chemical nanomaterial syntheses. Fouling origins and consequences are discussed together with the variety of flow reactors for its prevention.

Big Data in a Nano World: A Review on Computational, Data-Driven Design of Nanomaterials Structures, Properties, and Synthesis

The recent rise of computational, data-driven research has significant potential to accelerate materials discovery. Automated workflows and materials databases are being rapidly developed, contributing to high-throughput data of bulk materials that are growing in quantity and complexity, allowing for correlation between structural-chemical features and functional properties. In contrast, computational data-driven approaches are still relatively rare for nanomaterials discovery due to the rapid scaling of computational cost for finite systems. However, the distinct behaviors at the nanoscale as compared to the parent bulk materials and the vast tunability space with respect to dimensionality and morphology motivate the development of data sets for nanometric materials. In this review, we discuss the recent progress in data-driven research in two aspects: functional materials design and guided synthesis, including commonly used metrics and approaches for designing materials properties and predicting synthesis routes. More importantly, we discuss the distinct behaviors of materials as a result of nanosizing and the implications for data-driven research. Finally, we share our perspectives on future directions for extending the current data-driven research into the nano realm.

Autonomous Multi-Step and Multi-Objective Optimization Facilitated by Real-Time Process Analytics

Autonomous flow reactors are becoming increasingly utilized in the synthesis of organic compounds, yet the complexity of the chemical reactions and analytical methods remains limited. The development of a modular platform which uses rapid flow NMR and FTIR measurements, combined with chemometric modeling, is presented for efficient and timely analysis of reaction outcomes. This platform is tested with a four variable single-step reaction (nucleophilic aromatic substitution), to determine the most effective optimization methodology. The self-optimization approach with minimal background knowledge proves to provide the optimal reaction parameters within the shortest operational time. The chosen approach is then applied to a seven variable two-step optimization problem (imine formation and cyclization), for the synthesis of the active pharmaceutical ingredient edaravone. Despite the exponentially increased complexity of this optimization problem, the platform achieves excellent results in a relatively small number of iterations, leading to >95% solution yield of the intermediate and up to 5.42 kg L-1 h-1 space-time yield for this pharmaceutically relevant product.

Flow Chemistry: A Sustainable Voyage Through the Chemical Universe en Route to Smart Manufacturing

Microfluidic devices and systems have entered many areas of chemical engineering, and the rate of their adoption is only increasing. As we approach and adapt to the critical global challenges we face in the near future, it is important to consider the capabilities of flow chemistry and its applications in next-generation technologies for sustainability, energy production, and tailor-made specialty chemicals. We present the introduction of microfluidics into the fundamental unit operations of chemical engineering. We discuss the traits and advantages of microfluidic approaches to different reactive systems, both well-established and emerging, with a focus on the integration of modular microfluidic devices into high-efficiency experimental platforms for accelerated process optimization and intensified continuous manufacturing. Finally, we discuss the current state and new horizons in self-driven experimentation in flow chemistry for both intelligent exploration through the chemical universe and distributed manufacturing. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Machine-Learning-Guided Discovery of 19F MRI Agents Enabled by Automated Copolymer Synthesis

Modern polymer science suffers from the curse of multidimensionality. The large chemical space imposed by including combinations of monomers into a statistical copolymer overwhelms polymer synthesis and characterization technology and limits the ability to systematically study structure-property relationships. To tackle this challenge in the context of 19F magnetic resonance imaging (MRI) agents, we pursued a computer-guided materials discovery approach that combines synergistic innovations in automated flow synthesis and machine learning (ML) method development. A software-controlled, continuous polymer synthesis platform was developed to enable iterative experimental-computational cycles that resulted in the synthesis of 397 unique copolymer compositions within a six-variable compositional space. The nonintuitive design criteria identified by ML, which were accomplished by exploring <0.9% of the overall compositional space, lead to the identification of >10 copolymer compositions that outperformed state-of-the-art materials.

Accelerated screening of colloidal nanocrystals using artificial neural network-assisted autonomous flow reactor technology

Colloidal semiconductor nanocrystals with tunable optical and electronic properties are opening up exciting opportunities for high-performance optoelectronics, photovoltaics, and bioimaging applications. Identifying the optimal synthesis conditions and screening of synthesis recipes in search of efficient synthesis pathways to obtain nanocrystals with desired optoelectronic properties, however, remains one of the major bottlenecks for accelerated discovery of colloidal nanocrystals. Conventional strategies, often guided by limited understanding of the underlying mechanisms remain expensive in both time and resources, thus significantly impeding the overall discovery process. In response, an autonomous experimentation platform is presented as a viable approach for accelerated synthesis screening and optimization of colloidal nanocrystals. Using a machine-learning-based predictive synthesis approach, integrated with automated flow reactor and inline spectroscopy, indium phosphide nanocrystals are autonomously synthesized. Their polydispersity for different target absorption wavelengths across the visible spectrum is simultaneously optimized during the autonomous experimentation, while utilizing minimal self-driven experiments (less than 50 experiments within 2 days). Starting with no-prior-knowledge of the synthesis, an ensemble neural network is trained through autonomous experiments to accurately predict the reaction outcome across the entire synthesis parameter space. The predicted parameter space map also provides new nucleation-growth kinetic insights to achieve high monodispersity in size of colloidal nanocrystals.

Toward autonomous design and synthesis of novel inorganic materials

Autonomous experimentation driven by artificial intelligence (AI) provides an exciting opportunity to revolutionize inorganic materials discovery and development. Herein, we review recent progress in the design of self-driving laboratories, including robotics to automate materials synthesis and characterization, in conjunction with AI to interpret experimental outcomes and propose new experimental procedures. We focus on efforts to automate inorganic synthesis through solution-based routes, solid-state reactions, and thin film deposition. In each case, connections are made to relevant work in organic chemistry, where automation is more common. Characterization techniques are primarily discussed in the context of phase identification, as this task is critical to understand what products have formed during synthesis. The application of deep learning to analyze multivariate characterization data and perform phase identification is examined. To achieve "closed-loop" materials synthesis and design, we further provide a detailed overview of optimization algorithms that use active learning to rationally guide experimental iterations. Finally, we highlight several key opportunities and challenges for the future development of self-driving inorganic materials synthesis platforms.

Expanding the Tool Kit of Automated Flow Synthesis: Development of In-line Flash Chromatography Purification

Recent advancements in in-line extraction and purification technology have enabled complex multistep synthesis in continuous flow reactor systems. However, for the large scope of chemical reactions that yield mixtures of products or residual starting materials, off-line purification is still required to isolate the desired compound. We present the in-line integration of a commercial automated flash chromatography system with a flow reactor for the continuous synthesis and isolation of product(s). A proof-of-principle study was performed to validate the system and test the durability of the column cartridges, performing an automated sequence of 100 runs over 2 days. Three diverse reaction systems that highlight the advantages of flow synthesis were successfully applied with in-line normal- or reversed-phase flash chromatography, continuously isolating products with 97-99% purity. Productivity of up to 9.9 mmol/h was achieved, isolating gram quantities of pure product from a feed of crude reaction mixture. Herein, we describe the development and optimization of the systems and suggest guidelines for selecting reactions well suited to in-line flash chromatography.

Continuous biphasic chemical processes in a four-phase segmented flow reactor

A four-phase segmented flow regime for continuous biphasic reaction processes is introduced, characterized over 1500 automatically conducted experiments, and used for biphasic ligand exchange of CdSe quantum dots.