Automated crystal system identification from electron diffraction patterns using multiview opinion fusion machine learning.

A bottleneck in high-throughput nanomaterials discovery is the pace at which new materials can be structurally characterized. Although current machine learning (ML) methods show promise for the automated processing of electron diffraction patterns (DPs), they fail in high-throughput experiments where DPs are collected from crystals with random orientations. Inspired by the human decision-making process, a framework for automated crystal system classification from DPs with arbitrary orientations was developed. A convolutional neural network was trained using evidential deep learning, and the predictive uncertainties were quantified and leveraged to fuse multiview predictions. Using vector map representations of DPs, the framework achieves a testing accuracy of 0.94 in the examples considered, is robust to noise, and retains remarkable accuracy using experimental data. This work highlights the ability of ML to be used to accelerate experimental high-throughput materials data analytics.

Using Surface Composition and Energy to Control the Formation of Either Tetrahexahedral or Hexoctahedral High-Index Facet Nanostructures.

High-index facet nanoparticles with structurally complex shapes, such as tetrahexahedron (THH) and hexoctahedron (HOH), represent a class of materials that are important for catalysis, and the study of them provides a fundamental understanding of the relationship between surface structures and catalytic properties. However, the high surface energies render them thermodynamically unfavorable compared to low-index facets, thereby making their syntheses challenging. Herein, we report a method to control the shape of high-index facet Cu nanoparticles (either THH with {210} facets or HOH with {421} facets) by tuning the facet surface energy with trace amounts of Te atoms. Density functional theory (DFT) calculations reveal that the density of Te atoms on Cu nanoparticles can change the relative stability of the high-index facets associated with either the THH or HOH structures. By controlling the annealing conditions and the rate of Te dealloying from CuTe nanoparticles, the surface density of Te atoms can be deliberately adjusted, which can be used to force the formation of either THH (higher surface Te density) or HOH (lower surface Te density) nanoparticles.

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.

Molecular Thin Films Enable the Synthesis and Screening of Nanoparticle Megalibraries Containing Millions of Catalysts.

Megalibraries are centimeter-scale chips containing millions of materials synthesized in parallel using scanning probe lithography. As such, they stand to accelerate how materials are discovered for applications spanning catalysis, optics, and more. However, a long-standing challenge is the availability of substrates compatible with megalibrary synthesis, which limits the structural and functional design space that can be explored. To address this challenge, thermally removable polystyrene films were developed as universal substrate coatings that decouple lithography-enabled nanoparticle synthesis from the underlying substrate chemistry, thus providing consistent lithography parameters on diverse substrates. Multi-spray inking of the scanning probe arrays with polymer solutions containing metal salts allows patterning of >56 million nanoreactors designed to vary in composition and size. These are subsequently converted to inorganic nanoparticles via reductive thermal annealing, which also removes the polystyrene to deposit the megalibrary. Megalibraries with mono-, bi-, and trimetallic materials were synthesized, and nanoparticle size was controlled between 5 and 35 nm by modulating the lithography speed. Importantly, the polystyrene coating can be used on conventional substrates like Si/SiOx, as well as substrates typically more difficult to pattern on, such as glassy carbon, diamond, TiO2, BN, W, or SiC. Finally, high-throughput materials discovery is performed in the context of photocatalytic degradation of organic pollutants using Au-Pd-Cu nanoparticle megalibraries on TiO2 substrates with 2,250,000 unique composition/size combinations. The megalibrary was screened within 1 h by developing fluorescent thin-film coatings on top of the megalibrary as proxies for catalytic turnover, revealing Au0.53Pd0.38Cu0.09-TiO2 as the most active photocatalyst composition.

Iridium-Incorporated Strontium Tungsten Oxynitride Perovskite for Efficient Acidic Hydrogen Evolution.

Heteroanionic materials exhibit great structural diversity with adjustable electronic, magnetic, and optical properties that provide immense opportunities for materials design. Within this material family, perovskite oxynitrides incorporate earth-abundant nitrogen with differing size, electronegativity, and charge into oxide, enabling a unique approach to tuning metal-anion covalency and energy of metal cation electronic states, thereby achieving functionality that may be inaccessible from their perovskite oxide counterparts, which have been widely studied as electrocatalysts. However, it is very challenging to directly obtain such materials due to the poor thermal stability of late transition metals coordinated with N and/or at high valence states. Herein, we introduce an effective strategy to prepare a perovskite oxynitride with a small fraction of sites substituted with Ir and adopt it as the first electrocatalyst in this material family, thereby enabling high activity and efficient utilization of precious metal content. From a series of characterization techniques, including X-ray absorption spectroscopy, atomic resolution electron microscopy, X-ray photoelectron spectroscopy, and X-ray diffraction, we prove the successful incorporation of Ir into a strontium tungsten oxynitride perovskite structure and discover the formation of a unique Ir-N/O coordination structure. Benefitting from this, the material exhibits a high activity toward the hydrogen evolution reaction, which exhibits an ultralow overpotential of only 8 mV to reach 10 mA/cm2geo in 0.5 M H2SO4 and 4.5-fold enhanced mass activity compared to commercial Pt/C. This work opens a new avenue for oxynitride material synthesis as well as pursuit of a new class of high-performance electrocatalysts.

Discovering polyelemental nanostructures with redistributed plasmonic modes through combinatorial synthesis.

Coupling plasmonic and functional materials provides a promising way to generate multifunctional structures. However, finding plasmonic nanomaterials and elucidating the roles of various geometric and dielectric configurations are tedious. This work describes a combinatorial approach to rapidly exploring and identifying plasmonic heteronanomaterials. Symmetry-broken noble/non-noble metal particle heterojunctions (~100 nanometers) were synthesized on multiwindow silicon chips with silicon nitride membranes. The metal types and the interface locations were controlled to establish a nanoparticle library, where the particle morphology and scattering color can be rapidly screened. By correlating structural data with near- and far-field single-particle spectroscopy data, we found that certain low-energy plasmonic modes could be supported across the heterointerface, while others are localized. Furthermore, we found a series of triangular heteronanoplates stabilized by epitaxial Moiré superlattices, which show strong plasmonic responses despite largely comprising a lossy metal (~70 atomic %). These architectures can become the basis for multifunctional and cost-effective plasmonic devices.

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 learning­driven, 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.