Summary Solutions to many of the world's problems depend upon materials research and development. However, advanced materials can take decades to discover and decades more to fully deploy. Humans and robots have begun to partner to advance science and technology orders of magnitude faster than humans do today through the development and exploitation of closed-loop, autonomous experimentation systems. This review discusses the specific challenges and opportunities related to materials discovery and development that will emerge from this new paradigm. Our perspective incorporates input from stakeholders in academia, industry, government laboratories, and funding agencies. We outline the current status, barriers, and needed investments, culminating with a vision for the path forward. We intend the article to spark interest in this emerging research area and to motivate potential practitioners by illustrating early successes. We also aspire to encourage a creative reimagining of the next generation of materials science infrastructure. To this end, we frame future investments in materials science and technology, hardware and software infrastructure, artificial intelligence and autonomy methods, and critical workforce development for autonomous research.

Autonomous experimentation systems for materials development: A community perspective

Many properties of nanoparticles are governed by their shape, size, polydispersity and surface chemistry. To apply nanoparticles in chemical sensing, medical diagnostics, catalysis, thermoelectrics, photovoltaics or pharmaceutics, they have to be synthesized with precisely controlled characteristics. This is a time-consuming, laborious and resource-intensive task, because nanoparticle syntheses often include multiple reagents and are conducted under interdependent experimental conditions. Machine learning (ML) offers a promising tool for the accelerated development of efficient protocols for nanoparticle synthesis and, potentially, for the synthesis of new types of nanoparticles. In this Review, we discuss ML algorithms that can be used for nanoparticle synthesis and highlight key approaches for the collection of large datasets. We examine ML-guided synthesis of semiconductor, metal, carbon-based and polymeric nanoparticles, and conclude with a discussion of current limitations, advantages and perspectives in the development of ML-assisted nanoparticle synthesis. Machine learning can be applied for the controlled synthesis of nanoparticles with precise properties. This Review discusses different machine learning approaches for the synthesis of semiconductor, metal, carbon-based and polymeric nanoparticles, and highlights key approaches for the collection of large datasets.

Nanoparticle synthesis assisted by machine learning

Self-Driving Platform for Metal Nanoparticle Synthesis: Combining Microfluidics and Machine Learning

Useful materials must satisfy multiple objectives, where the optimization of one objective is often at the expense of another. The Pareto front reports the optimal trade-offs between these conflicting objectives. Here we use a self-driving laboratory, Ada, to define the Pareto front of conductivities and processing temperatures for palladium films formed by combustion synthesis. Ada discovers new synthesis conditions that yield metallic films at lower processing temperatures (below 200 °C) relative to the prior art for this technique (250 °C). This temperature difference makes possible the coating of different commodity plastic materials (e.g., Nafion, polyethersulfone). These combustion synthesis conditions enable us to to spray coat uniform palladium films with moderate conductivity (1.1 × 105 S m-1) at 191 °C. Spray coating at 226 °C yields films with conductivities (2.0 × 106 S m-1) comparable to those of sputtered films (2.0 to 5.8 × 106 S m-1). This work shows how a self-driving laboratoy can discover materials that provide optimal trade-offs between conflicting objectives. 

https://www.nature.com/articles/s41467-022-28580-6.pdf

A self-driving laboratory advances the Pareto front for material properties

In the field of machine learning (ML) for materials optimization, active learning algorithms, such as Bayesian Optimization (BO), have been leveraged for guiding autonomous and high-throughput experimentation systems. However, very few studies have evaluated the efficiency of BO as a general optimization algorithm across a broad range of experimental materials science domains. In this work, we evaluate the performance of BO algorithms with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems, namely carbon nanotube polymer blends, silver nanoparticles, lead-halide perovskites, as well as additively manufactured polymer structures and shapes. By defining acceleration and enhancement metrics for general materials optimization objectives, we find that for surrogate model selection, Gaussian Process (GP) with anisotropic kernels (automatic relevance detection, ARD) and Random Forests (RF) have comparable performance and both outperform the commonly used GP without ARD. We discuss the implicit distributional assumptions of RF and GP, and the benefits of using GP with anisotropic kernels in detail. We provide practical insights for experimentalists on surrogate model selection of BO during materials optimization campaigns.

Benchmarking the performance of Bayesian optimization across multiple experimental materials science domains

In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.

/pdf/two-step-machine-learning-enables-optimized-nanoparticle-1dzeypd5or.pdf

Two-step machine learning enables optimized nanoparticle synthesis

In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with a desired absorbance spectrum. Combining a Gaussian Process based Bayesian Optimization (BO) with a Deep Neural Network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis, and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.

/pdf/two-step-machine-learning-enables-optimized-nanoparticle-2bmut4ucrx.pdf

Zackaria Mahfoud

Papers

Two-step machine learning enables optimized nanoparticle synthesis

Two-Step Machine Learning Enables Optimized Nanoparticle Synthesis