A density functional theory parameterised neural network model of zirconia

Unveiling Carbon Cluster Coating in Graphene CVD on MgO: Combining Machine Learning Force field and DFT Modeling

In this study, we investigate the behavior of carbon clusters (Cn, where n ranges from 16 to 26) supported on the surface of MgO. We consider the impact of doping with common impurities (such as Si, Mn, Ca, Fe, and Al) that are typically found in ores. Our approach combines density functional theory calculations with machine learning force field molecular dynamics simulations. It is found that the C21 cluster, featuring a core-shell structure composed of three pentagons isolated by three hexagons, demonstrates exceptional stability on the MgO surface and behaves as an "enhanced binding agent" on MgO-doped surfaces. The molecular dynamics trajectories reveal that the stable C21 coating on the MgO surface exhibits less mobility compared to other sizes Cn clusters and the flexible graphene layer on MgO. Furthermore, this stability persists even at temperatures up to 1100K. The analysis of the electron localization function and potential function of Cn on MgO reveals the high localization electron density between the central carbon of the C21 ring and the MgO surface. This work proposes that the C21 island serves as a superstable and less mobile precursor coating on MgO surfaces. This explanation sheds light on the experimental defects observed in graphene products, which can be attributed to the reduced mobility of carbon islands on a substrate that remains frozen and unchanged.

First-principles data for solid solution niobium-tantalum-vanadium alloys with body-centered-cubic structures

We present four open-source datasets that provide results of density functional theory (DFT) calculations of ground-state properties of refractory solid solution binary alloys niobium-tantalum (NbTa), niobium-vanadium (NbV), tantalum-vanadium (TaV), and ternary alloys NbTaV ordered in body-centered-cubic (BCC) structures with 128 Bravais lattice sites. The first-principles code used to run the calculations is the Vienna Ab-Initio Simulation Package. The calculations have been collected by uniformly sampling chemical compositions across the entire compositional range. For each chemical composition, the calculations have been run for 100 randomized arrangements of the constituents on the BCC lattice sites. This sampling methodology resulted in running DFT simulations for a total of 3,100 randomized atomic configurations over 31 chemical compositions for each of the three binary alloys Nb-Ta, Nb-V, Ta-V, and a total of 10,500 randomized atomic structures over 105 chemical compositions for the ternary alloys Nb-Ta-V. For each atomic configuration, geometry optimization has been performed, and the data released contains information about each step of geometry optimization for each atomic configuration.

Benchmarking structural evolution methods for training of machine learned interatomic potentials

When creating training data for machine-learned interatomic potentials (MLIPs), it is common to create initial structures and evolve them using molecular dynamics (MD) to sample a larger configuration space. We benchmark two other modalities of evolving structures, contour exploration (CE) and dimer-method (DM) searches against MD for their ability to produce diverse and robust density functional theory training data sets for MLIPs. We also discuss the generation of initial structures which are either from known structures or from random structures in detail to further formalize the structure-sourcing processes in the future. The polymorph-rich zirconium-oxygen composition space is used as a rigorous benchmark system for comparing the performance of MLIPs trained on structures generated from these structural evolution methods. Using Behler-Parrinello neural networks as our MLIP models, we find that CE and the DM searches are generally superior to MD in terms of spatial descriptor diversity and statistical accuracy.

Artificial Intelligence in Biomedical Applications of Zirconia

Artificial intelligence (AI) is rapidly developed based on computer technology, which can perform tasks that customarily require human intelligence by building intelligent software or machines. As a subfield of AI, machine learning (ML) can learn from the intrinsic statistical patterns and structures in data through algorithms to predict invisible data. With the increasing interest in aesthetics in dentistry, zirconia has drawn lots of attention due to its superior biocompatibility, aesthetically pleasing, high corrosion resistance, good mechanical properties, and absence of reported allergic reactions. The evolution of AI and ML led to the development of novel approaches for the biomedical applications of zirconia in dental devices. AI techniques in zirconia-related research and clinical applications have attracted much attention due to their ability to analyze data and reveal correlations between complex phenomena. The AI applications in the field of zirconia science change according to the application direction of zirconia. Therefore, in this article, we focused on AI in biomedical applications of zirconia in dental devices and AI in zirconia-related applications in dentistry.

Fast and stable deep-learning predictions of material properties for solid solution alloys

We present a novel deep learning (DL) approach to produce highly accurate predictions of macroscopic physical properties of solid solution binary alloys and magnetic systems. The major idea is to make use of the correlations between different physical properties in alloy systems to improve the prediction accuracy of neural network (NN) models. We use multitasking NN models to simultaneously predict the total energy, charge density and magnetic moment. These physical properties mutually serve as constraints during the training of the multitasking NN, resulting in more reliable DL models because multiple physics properties are correctly learned by a single model. Two binary alloys, copper-gold (CuAu) and iron-platinum (FePt), were studied. Our results show that once the multitasking NN's are trained, they can estimate the material properties for a specific configuration hundreds of times faster than first-principles density functional theory calculations while retaining comparable accuracy. We used a simple measure based on the root-mean-squared errors to quantify the quality of the NN models, and found that the inclusion of charge density and magnetic moment as physical constraints leads to more stable models that exhibit improved accuracy and reduced uncertainty for the energy predictions.