Machine Learning-Enabled Image Classification for Automated Electron Microscopy

Traditionally, materials discovery has been driven more by evidence and intuition than by systematic design. However, the advent of "big data" and an exponential increase in computational power have reshaped the landscape. Today, we use simulations, artificial intelligence (AI), and machine learning (ML) to predict materials characteristics, which dramatically accelerates the discovery of novel materials. For instance, combinatorial megalibraries, where millions of distinct nanoparticles are created on a single chip, have spurred the need for automated characterization tools. This paper presents an ML model specifically developed to perform real-time binary classification of grayscale high-angle annular dark-field images of nanoparticles sourced from these megalibraries. Given the high costs associated with downstream processing errors, a primary requirement for our model was to minimize false positives while maintaining efficacy on unseen images. We elaborate on the computational challenges and our solutions, including managing memory constraints, optimizing training time, and utilizing Neural Architecture Search tools. The final model outperformed our expectations, achieving over 95% precision and a weighted F-score of more than 90% on our test data set. This paper discusses the development, challenges, and successful outcomes of this significant advancement in the application of AI and ML to materials discovery.

Examining graph neural networks for crystal structures: Limitations and opportunities for capturing periodicity

Graph neural networks (GNNs) have recently been used to learn the representations of crystal structures through an end-to-end data-driven approach. However, a systematic top-down approach to evaluate and understand the limitations of GNNs in accurately capturing crystal structures has yet to be established. In this study, we introduce an approach using human-designed descriptors as a compendium of human knowledge to investigate the extent to which GNNs can comprehend crystal structures. Our findings reveal that current state-of-the-art GNNs fall short in accurately capturing the periodicity of crystal structures. We analyze this failure by exploring three aspects: local expressive power, long-range information processing, and readout function. To address these identified limitations, we propose a straightforward and general solution: the hybridization of descriptors with GNNs, which directly supplements the missing information to GNNs. The hybridization enhances the predictive accuracy of GNNs for specific material properties, most notably phonon internal energy and heat capacity, which heavily rely on the periodicity of materials.

Making Meaning Together: Co-designing a Social Robot for Older Adults with Ikigai Experts

A sense of meaning and purpose in life-known in Japan as one's ikigai-can lead to better health outcomes, an improved sense of well-being, and longer life as people age. The design of socially assistive robots, however, has so far focused largely on the more hedonic aims of supporting positive affect and happiness through interactions with robots. To explore how social robots might be able to support people's ikigai, we performed (1) in-depth interviews with 12 'ikigai experts' who formally support and/or study older adults (OAs)' ikigai and (2) 5 co-design workshop sessions with 10 such experts. Our interview findings show that expert practitioners define ikigai in a holistic way in their everyday experience and practice, incorporating physical, social, and mental activities that relate not only to the individual and their behaviors, but also to their relationships with other people and to their connection with the broader community (3 levels of ikigai). Our co-design workshops showed that ikigai experts were overall positive towards the use of social robots to support OAs' ikigai, particularly in the roles of an information-provider and social enabler that connects OAs to other people and activities in their communities. They also point out areas of potential risk, including the need to maintain OAs' independence, relationships with others, and privacy, which should be considered in design. This research is the first to explore the co-design of social robots that can support people's sense of ikigai-meaning and purpose-as they age.

Chemistry-Informed Machine Learning for Polymer Electrolyte Discovery

Solid polymer electrolytes (SPEs) have the potential to improve lithium-ion batteries by enhancing safety and enabling higher energy densities. However, SPEs suffer from significantly lower ionic conductivity than liquid and solid ceramic electrolytes, limiting their adoption in functional batteries. To facilitate more rapid discovery of high ionic conductivity SPEs, we developed a chemistry-informed machine learning model that accurately predicts ionic conductivity of SPEs. The model was trained on SPE ionic conductivity data from hundreds of experimental publications. Our chemistry-informed model encodes the Arrhenius equation, which describes temperature activated processes, into the readout layer of a state-of-the-art message passing neural network and has significantly improved accuracy over models that do not encode temperature dependence. Chemically informed readout layers are compatible with deep learning for other property prediction tasks and are especially useful where limited training data are available. Using the trained model, ionic conductivity values were predicted for several thousand candidate SPE formulations, allowing us to identify promising candidate SPEs. We also generated predictions for several different anions in poly(ethylene oxide) and poly(trimethylene carbonate), demonstrating the utility of our model in identifying descriptors for SPE ionic conductivity.

Machine learning-accelerated design and synthesis of polyelemental heterostructures

In materials discovery efforts, synthetic capabilities far outpace the ability to extract meaningful data from them. To bridge this gap, machine learning methods are necessary to reduce the search space for identifying desired materials. Here, we present a machine learning–driven, closed-loop experimental process to guide the synthesis of polyelemental nanomaterials with targeted structural properties. By leveraging data from an eight-dimensional chemical space (Au-Ag-Cu-Co-Ni-Pd-Sn-Pt) as inputs, a Bayesian optimization algorithm is used to suggest previously unidentified nanoparticle compositions that target specific interfacial motifs for synthesis, results of which are iteratively shared back with the algorithm. This feedback loop resulted in successful syntheses of 18 heterojunction nanomaterials that are too complex to discover by chemical intuition alone, including extremely chemically complex biphasic nanoparticles reported to date. Platforms like the one developed here are poised to transform materials discovery across a wide swath of applications and industries.

Screening and Understanding Li Adsorption on Two-Dimensional Metallic Materials by Learning Physics and Physics-Simplified Learning

Understanding and broad screening Li interaction energetics with surfaces are key to the development of materials for a wide range of applications including Li-based electrochemical capacitors, Li sensors, Li separation membranes, and Li-ion batteries. In this work, we build a high-throughput screening scheme to screen Li adsorption energetics on 2D metallic materials. First, density functional theory and graph convolution networks are utilized to calculate the minimum Li adsorption energies for some 2D metallic materials. The data is then used to find a dependence of the minimum Li adsorption energies on the sum of ionization potential, work function of the 2D metal, and coupling energy between Li⁺ and substrate, and the dependence is used to screen all 2D metallic materials. Physics-simplified learning by splitting the property into different contributions and learning or calculating each component is shown to have higher accuracy and transferability for machine learning of complex materials properties.

Electrochemical oxidation of molecular nitrogen to nitric acid - towards a molecular level understanding of the challenges

Nitric acid is manufactured by oxidizing ammonia where the ammonia comes from an energy demanding and non-eco-friendly, Haber-Bosch process. Electrochemical oxidation of N2 to nitric acid using renewable electricity could be a promising alternative to bypass the ammonia route. In this work, we discuss the plausible reaction mechanisms of electrochemical N2 oxidation (N2OR) at the molecular level and its competition with the parasitic oxygen evolution reaction (OER). We suggest the design strategies for N2 oxidation electro-catalysts by first comparing the performance of two catalysts - TiO2(110) (poor OER catalyst) and IrO2(110) (good OER catalyst), towards dinitrogen oxidation and then establish trends/scaling relations to correlate OER and N2OR activities. The challenges associated with electrochemical N2OR are highlighted.

The phase stability network of all inorganic materials

One of the holy grails of materials science, unlocking structure-property relationships, has largely been pursued via bottom-up investigations of how the arrangement of atoms and interatomic bonding in a material determine its macroscopic behavior. Here, we consider a complementary approach, a top-down study of the organizational structure of networks of materials, based on the interaction between materials themselves. We unravel the complete "phase stability network of all inorganic materials" as a densely connected complex network of 21,000 thermodynamically stable compounds (nodes) interlinked by 41 million tie line (edges) defining their two-phase equilibria, as computed by high-throughput density functional theory. Analyzing the topology of this network of materials has the potential to uncover previously unidentified characteristics inaccessible from traditional atoms-to-materials paradigms. Using the connectivity of nodes in the phase stability network, we derive a rational, data-driven metric for material reactivity, the "nobility index," and quantitatively identify the noblest materials in nature.

Soft nanocomposite electroadhesives for digital micro- and nanotransfer printing

Automated handling of microscale objects is essential for manufacturing of next-generation electronic systems. Yet, mechanical pick-and-place technologies cannot manipulate smaller objects whose surface forces dominate over gravity, and emerging microtransfer printing methods require multidirectional motion, heating, and/or chemical bonding to switch adhesion. We introduce soft nanocomposite electroadhesives (SNEs), comprising sparse forests of dielectric-coated carbon nanotubes (CNTs), which have electrostatically switchable dry adhesion. SNEs exhibit 40-fold lower nominal dry adhesion than typical solids, yet their adhesion is increased >100-fold by applying 30 V to the CNTs. We characterize the scaling of adhesion with surface morphology, dielectric thickness, and applied voltage and demonstrate digital transfer printing of films of Ag nanowires, polymer and metal microparticles, and unpackaged light-emitting diodes.

Network analysis of synthesizable materials discovery

Assessing the synthesizability of inorganic materials is a grand challenge for accelerating their discovery using computations. Synthesis of a material is a complex process that depends not only on its thermodynamic stability with respect to others, but also on factors from kinetics, to advances in synthesis techniques, to the availability of precursors. This complexity makes the development of a general theory or first-principles approach to synthesizability currently impractical. Here we show how an alternative pathway to predicting synthesizability emerges from the dynamics of the materials stability network: a scale-free network constructed by combining the convex free-energy surface of inorganic materials computed by high-throughput density functional theory and their experimental discovery timelines extracted from citations. The time-evolution of the underlying network properties allows us to use machine-learning to predict the likelihood that hypothetical, computer-generated materials will be amenable to successful experimental synthesis.