Inverse Design of Nanoparticles Using Multi‐Target Machine Learning

Structural classification of Ag and Cu nanocrystals with machine learning

We use machine learning (ML) to classify the structures of mono-metallic Cu and Ag nanoparticles. Our datasets comprise a broad range of structures - both crystalline and amorphous - derived from parallel-tempering molecular dynamics simulations of nanoparticles in the 100-200 atom size range. We construct nanoparticle features using common neighbor analysis (CNA) signatures, and we utilize principal component analysis to reduce the dimensionality of the CNA feature set. To sort the nanoparticles into structural classes, we employed both K-means clustering and the Gaussian mixture model (GMM). We evaluated the performance of the clustering algorithms through the gap statistic and silhouette score, as well as by analysis of the CNA signatures. For Ag, we found five structural classes, with 14 detailed sub-classes, while for Cu, we found two broad classes (crystalline and amorphous), with the same five classes as for Ag, and 15 detailed sub-classes. Our results demonstrate that these ML methods are effective in identifying and categorizing nanoparticle structures to different levels of complexity, enabling us to classify nanoparticles into distinct and physically relevant structural classes with high accuracy. This capability is important for understanding nanoparticle properties and potential applications.

Single-Atom Heterogeneous Catalysts: Human- and AI-Driven Platform for Augmented Designs, Analytics and Reality-Enabled Manufacturing

Heterogeneous catalysts with targeted functionality can be designed with atomic precision, but it is challenging to retain the structure and performance upon the scaled-up manufacturing. Particularly challenging is to ensure the "atomic economy", where every catalytic site is most gainfully utilized. Given the emerging synergistic integration of human- and artificial intelligence (AI)-driven augmented designs (AD), augmented analytics (AA), and augmented reality manufacturing (AM) platforms, this minireview focuses on single-atom heterogeneous catalysts (SAHCs) and examines the current status, challenges, and future perspectives of translating atomic-level structural precision and data-driven discovery to next-generation industrial manufacturing. We critically examine the atomistic insights into structure-driven SAHCs functionality and discuss the opportunities and challenges on the way towards the synergistic human-AI collaborative data-driven platform capable of monitoring, analyzing, manufacturing, and retaining the atomic-scale structure and functions. Enhanced by the atomic-level AD, AA, and AM, evolving from the current high-throughput capabilities and digital materials manufacturing acceleration, this synergistic human-AI platform is promising to enable atom-efficient and atomically precise heterogeneous catalyst production.

Application of Machine Learning in Material Synthesis and Property Prediction

Material innovation plays a very important role in technological progress and industrial development. Traditional experimental exploration and numerical simulation often require considerable time and resources. A new approach is urgently needed to accelerate the discovery and exploration of new materials. Machine learning can greatly reduce computational costs, shorten the development cycle, and improve computational accuracy. It has become one of the most promising research approaches in the process of novel material screening and material property prediction. In recent years, machine learning has been widely used in many fields of research, such as superconductivity, thermoelectrics, photovoltaics, catalysis, and high-entropy alloys. In this review, the basic principles of machine learning are briefly outlined. Several commonly used algorithms in machine learning models and their primary applications are then introduced. The research progress of machine learning in predicting material properties and guiding material synthesis is discussed. Finally, a future outlook on machine learning in the materials science field is presented.

Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)-toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

Safety-by-design using forward and inverse multi-target machine learning

The economic and social future of nanotechnology depends on our ability and manufacture nanomaterials that avoid potential toxicity, by identifying them before they are made, used and released into the environment. Safety-by-design is a framework for including these issues at an early stage of the development process, but balancing multiple nanoparticle properties and selection criteria remains challenging. Based on a synthetic data set of over 19,000 possible sunscreen product specifications, we have used multi-target machine learning to predict the corresponding size, shape, concentration and polytype of titania nanoparticle additives. The study considers the optical properties responsible for the sun protection factor and product transparency, including the extinction coefficients for ultra violet and visible light, and the potential for toxicity due to the generation of reactive oxygen species from the photocatalytically active facets of both anatase and rutile nanoparticles, as a function of the size and shape. We predict a number of conventional forward structure/property and property/product relationships, but show that a direct structure/product relationship provides superior performance when predicting multiple properties or product specifications simultaneously. These models are then inverted, re-optimized and re-trained to provide focused, high performing inverse design models that do not require additional optimization, and are capable of identifying nanoparticle configurations outside of the training set. The ability to directly predict suitable nanoparticle structures that conform to prerequisite sun protection, transparently and potential toxicity thresholds represents a new approach to safety-by-design that can be applied to other products and materials where multiple design criteria must be met at the same time.