Development and Validation of Versatile Deep Atomistic Potentials for Metal Oxides

Overcoming Inaccuracies in Machine Learning Interatomic Potential Implementation for Ionic Vacancy Simulations

Machine learning interatomic potentials, particularly ones based on deep neural networks, have taken significant strides in accelerating first-principles simulations, expanding the length and time scales of the simulations with accuracies akin to first-principles simulations. Notwithstanding their success in accurately describing the physical properties of pristine ionic systems with multiple oxidation states, herein we show that an implementation of deep neural network potentials (DNPs) yield vacancy formation energies in MgO with a significant ∼3 eV error. In contrast, we show that moment tensor potentials can accurately describe all properties of the oxide, including vacancy formation energies. We show that the vacancy formation energy errors in DNPs correlate with the strength of ionic interactions in the system as evidenced by contrasting MgO with the less ionic systems CuxOy and AgxOy. Our findings suggest that descriptors employed in the DNP may be inadequate and cannot accurately describe vacancies in ionic systems.

Exploring the Crystal Structure and Electronic Properties of γ-Al2O3: Machine Learning Drives Future Material Innovations

For decades, researchers have struggled to determine the precise crystal structure of γ-Al2O3 due to its atomic-level disorder and the challenges associated with obtaining high-purity, high-crystallinity γ-Al2O3 in laboratory settings. This study investigates the crystal structure and electronic properties of γ-Al2O3 coatings under the influence of an external electric field, integrating machine learning with density functional theory (DFT). A potential 160-atom supercell structure was identified from over 600,000 γ-Al2O3 configurations and confirmed through high-resolution transmission electron microscopy and selected area electron diffraction. The findings indicate that γ-Al2O3 deviates from the conventional spinel structure, suggesting that octahedral vacancies can reduce the system's energy. Under an external electric field, the material's band structure and density of states (DOS) undergo significant changes: the bandgap narrows from 3.996 to 0 eV, resulting in metallic behavior, while the projected density of states (PDOS) exhibits peak broadening and splitting of oxygen atom PDOS below the Fermi level. These alterations elucidate the variations in the electrical conductivity of alumina coatings under an electric field. These findings clarify the mechanisms of γ-Al2O3's electronic property modulation and offer insights into its covalent and ionic mixed bonding as a wide-bandgap semiconductor. This discovery is essential for understanding dielectric breakdown in insulating materials.

Active sparse Bayesian committee machine potential for isothermal-isobaric molecular dynamics simulations

Recent advancements in machine learning potentials (MLPs) have significantly impacted the fields of chemistry, physics, and biology by enabling large-scale first-principles simulations. Among different machine learning approaches, kernel-based MLPs distinguish themselves through their ability to handle small datasets, quantify uncertainties, and minimize over-fitting. Nevertheless, their extensive computational requirements present considerable challenges. To alleviate these, sparsification methods have been developed, aiming to reduce computational scaling without compromising accuracy. In the context of isothermal and isobaric ML molecular dynamics (MD) simulations, achieving precise pressure estimation is crucial for reproducing reliable system behavior under constant pressure. Despite progress, sparse kernel MLPs struggle with precise pressure prediction. Here, we introduce a virial kernel function that significantly enhances the pressure estimation accuracy of MLPs. Additionally, we propose the active sparse Bayesian committee machine (BCM) potential, an on-the-fly MLP architecture that aggregates local sparse Gaussian process regression (SGPR) MLPs. The sparse BCM potential overcomes the steep computational scaling with the kernel size, and a predefined restriction on the size of kernel allows for fast and efficient on-the-fly training. Our advancements facilitate accurate and computationally efficient machine learning-enhanced MD (MLMD) simulations across diverse systems, including ice-liquid coexisting phases, Li10Ge(PS6)2 lithium solid electrolyte, and high-pressure liquid boron nitride.

Theoretical Prediction of Thermal Expansion Anisotropy for Y2Si2O7 Environmental Barrier Coatings Using a Deep Neural Network Potential and Comparison to Experiment

Environmental barrier coatings (EBCs) are an enabling technology for silicon carbide (SiC)-based ceramic matrix composites (CMCs) in extreme environments such as gas turbine engines. However, the development of new coating systems is hindered by the large design space and difficulty in predicting the properties for these materials. Density Functional Theory (DFT) has successfully been used to model and predict some thermodynamic and thermo-mechanical properties of high-temperature ceramics for EBCs, although these calculations are challenging due to their high computational costs. In this work, we use machine learning to train a deep neural network potential (DNP) for Y2Si2O7, which is then applied to calculate the thermodynamic and thermo-mechanical properties at near-DFT accuracy much faster and using less computational resources than DFT. We use this DNP to predict the phonon-based thermodynamic properties of Y2Si2O7 with good agreement to DFT and experiments. We also utilize the DNP to calculate the anisotropic, lattice direction-dependent coefficients of thermal expansion (CTEs) for Y2Si2O7. Molecular dynamics trajectories using the DNP correctly demonstrate the accurate prediction of the anisotropy of the CTE in good agreement with the diffraction experiments. In the future, this DNP could be applied to accelerate additional property calculations for Y2Si2O7 compared to DFT or experiments.

Exploring the formation of gold/silver nanoalloys with gas-phase synthesis and machine-learning assisted simulations

While nanoalloys are of paramount scientific and practical interest, the main processes leading to their formation are still poorly understood. Key structural features in the alloy systems, including the crystal phase, chemical ordering, and morphology, are challenging to control at the nanoscale, making it difficult to extend their use to industrial applications. In this contribution, we focus on the gold/silver system that has two of the most prevalent noble metals and combine experiments with simulations to uncover the formation mechanisms at the atomic level. Nanoparticles were produced using a state-of-the-art inert-gas aggregation source and analyzed using transmission electron microscopy and energy-dispersive X-ray spectroscopy. Machine-learning-assisted molecular dynamics simulations were employed to model the crystallization process from liquid droplets to nanocrystals. Our study finds a preponderance of nanoparticles with five-fold symmetric morphology, including icosahedra and decahedra which is consistent with previous results on mono-metallic nanoparticles. However, we observed that gold atoms, rather than silver atoms, segregate at the surface of the obtained nanoparticles for all the considered alloy compositions. These segregation tendencies are in contrast to previous studies and have consequences on the crystallization dynamics and the subsequent crystal ordering. We finally showed that the underpinning of this surprising segregation dynamics is due to charge transfer and electrostatic interactions rather than surface energy considerations.

ColabFit exchange: Open-access datasets for data-driven interatomic potentials

Data-driven interatomic potentials (IPs) trained on large collections of first principles calculations are rapidly becoming essential tools in the fields of computational materials science and chemistry for performing atomic-scale simulations. Despite this, apart from a few notable exceptions, there is a distinct lack of well-organized, public datasets in common formats available for use with IP development. This deficiency precludes the research community from implementing widespread benchmarking, which is essential for gaining insight into model performance and transferability, and also limits the development of more general, or even universal, IPs. To address this issue, we introduce the ColabFit Exchange, the first database providing open access to a large collection of systematically organized datasets from multiple domains that is especially designed for IP development. The ColabFit Exchange is publicly available at https://colabfit.org, providing a web-based interface for exploring, downloading, and contributing datasets. Composed of data collected from the literature or provided by community researchers, the ColabFit Exchange currently (September 2023) consists of 139 datasets spanning nearly 70 000 unique chemistries, and is intended to continuously grow. In addition to outlining the software framework used for constructing and accessing the ColabFit Exchange, we also provide analyses of the data, quantifying the diversity of the database and proposing metrics for assessing the relative diversity of multiple datasets. Finally, we demonstrate an end-to-end IP development pipeline, utilizing datasets from the ColabFit Exchange, fitting tools from the KLIFF software package, and validation tests provided by the OpenKIM framework.

Machine-Learning Accelerated First-Principles Accurate Modeling of the Solid-Liquid Phase Transition in MgO under Mantle Conditions

While accurate measurements of MgO under extreme high-pressure conditions are needed to understand and model planetary behavior, these studies are challenging from both experimental and computational modeling perspectives. Herein, we accelerate density functional theory (DFT) accurate calculations using deep neural network potentials (DNPs) trained over multiple phases and study the melting behavior of MgO via the two-phase coexistence (TPC) approach at 0-300 GPa and ≤9600 K. The resulting DNP-TPC melting curve is in excellent agreement with existing experimental studies. We show that the mitigation of finite-size effects that typically skew the predicted melting temperatures in DFT-TPC simulations in excess of several hundred kelvin requires models with ∼16 000 atoms and >100 ps molecular dynamics trajectories. In addition, the DNP can successfully describe MgO metallization well at increased pressures that are captured by DFT but missed by classical interatomic potentials.

ChecMatE: A workflow package to automatically generate machine learning potentials and phase diagrams for semiconductor alloys

Semiconductor alloy materials are highly versatile due to their adjustable properties; however, exploring their structural space is a challenging task that affects the control of their properties. Traditional methods rely on ad hoc design based on the understanding of known chemistry and crystallography, which have limitations in computational efficiency and search space. In this work, we present ChecMatE (Chemical Material Explorer), a software package that automatically generates machine learning potentials (MLPs) and uses global search algorithms to screen semiconductor alloy materials. Taking advantage of MLPs, ChecMatE enables a more efficient and cost-effective exploration of the structural space of materials and predicts their energy and relative stability with ab initio accuracy. We demonstrate the efficacy of ChecMatE through a case study of the InxGa1-xN system, where it accelerates structural exploration at reduced costs. Our automatic framework offers a promising solution to the challenging task of exploring the structural space of semiconductor alloy materials.