Accelerated mapping of electronic density of states patterns of metallic nanoparticles via machine-learning

Structure to Property: Chemical Element Embeddings for Predicting Electronic Properties of Crystals

We present a new general-purpose machine learning model that is able to predict a variety of crystal properties, including Fermi level energy and band gap, as well as spectral ones such as electronic densities of states. The model is based on atomic representations that enable it to effectively capture complex information about each atom and its surrounding environment in a crystal. The accuracy achieved for band gaps exceeds results previously published. By design, our model is not restricted to the electronic properties discussed here but can be extended to fit diverse chemical descriptors. Its advantages are (a) its low computational requirements, making it an efficient tool for high-throughput screening of materials; and (b) the simplicity and flexibility of its architecture, facilitating implementation and interpretation, especially for researchers in the field of computational chemistry.

Theoretical search for characteristic atoms in supported gold nanoparticles: a large-scale DFT study

The size and site dependences of atomic and electronic structures in isolated and supported gold nanoparticles have been investigated using large-scale density functional theory (DFT) calculations using multi-site support functions. The effects of the substrate on nanoparticles with diameters of 2 nm and several different shapes have been examined. First, isolated gold nanoparticles with diameters of 0.6 nm (13 atoms) to 4.5 nm (2057 atoms), which have comparable sizes to nanoparticles used in experiments, were considered. To analyse huge amounts of data obtained from large-scale DFT calculations, we performed principal component analysis (PCA), which helps systematically and efficiently clarify the electronic structures of large nanoparticles. The PCA results reveal the site dependence of the electronic structures. Notably, the atoms in the surface and subsurface have different electronic structures to those located in the inner layers, especially at the vertexes of the particles. The convergence of local electronic structures with respect to the particle size has also been demonstrated. For supported nanoparticles, PCA helps indicate which atoms are affected, and how much, by the substrate. The correlation between the PCA results and site dependence of reaction activity is also discussed herein.

Thin Film Resistance Gating by Redox Charge Exchange: Evidence for a Quantum Transition State

Field effect transistors (FETs) and related devices have enabled tremendous advances in electronics, as well as studies of fundamental phenomena. FETs are classically actuated as fields charge/discharge materials, thereby modifying their resistance. Here, we develop charge exchange transistors (CETs) that comprise thin films whose resistance is modified by quantum charge exchange processes, e.g., redox and bonding. We first use CETs to probe the metallocene-thin film interaction during cyclic voltammetry. Remarkably, CETs reveal transient resistance peaks associated with charge transfer during both oxidation and reduction. Our data combined with kinetics and density functional theory modeling are consistent with a multistep redox pathway, including the formation/destruction of a quantum transition state that overlaps molecule + thin film band states. As a further proof-of-principle demonstration, we also use CETs to monitor n-alkanethiol self-assembly on thin Au films in real-time. CETs exhibit monotonic resistance increase consistent with previously reported fast-then-slow kinetics attributed to thiol-thin film bond formation (charge localization) and etching and/or molecule reorganization.

Atomic Positional Embedding-Based Transformer Model for Predicting the Density of States of Crystalline Materials

The rapid advancement of machine learning has revolutionized quite a few science fields, leading to a surge in the development of highly efficient and accurate materials discovery methods. Recently, predictions of multiple related properties have received attention, with a particular emphasis on spectral properties, where the electronic density of states (DOS) stands out as the fundamental data with enormous potential to advance our understanding of crystalline materials. Leveraging the power of the Transformer framework, we introduce an Atomic Positional Embedding-Based Transformer (APET), which surpasses existing state-of-the-art models for predicting ab initio DOS. APET utilizes atomic periodical positions as its positional embedding, which incorporates all of the structural information in a crystal, providing a more complete and accurate representation. Furthermore, the interpretability of APET enables us to discover the underlying physical properties of materials with greater precision and accuracy.

Machine learning-enabled exploration of the electrochemical stability of real-scale metallic nanoparticles

Surface Pourbaix diagrams are critical to understanding the stability of nanomaterials in electrochemical environments. Their construction based on density functional theory is, however, prohibitively expensive for real-scale systems, such as several nanometer-size nanoparticles (NPs). Herein, with the aim of accelerating the accurate prediction of adsorption energies, we developed a bond-type embedded crystal graph convolutional neural network (BE-CGCNN) model in which four bonding types were treated differently. Owing to the enhanced accuracy of the bond-type embedding approach, we demonstrate the construction of reliable Pourbaix diagrams for very large-size NPs involving up to 6525 atoms (approximately 4.8 nm in diameter), which enables the exploration of electrochemical stability over various NP sizes and shapes. BE-CGCNN-based Pourbaix diagrams well reproduce the experimental observations with increasing NP size. This work suggests a method for accelerated Pourbaix diagram construction for real-scale and arbitrarily shaped NPs, which would significantly open up an avenue for electrochemical stability studies.

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.

Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings

Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec's ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.