A generalizable machine learning potential of Ag-Au nanoalloys and its application t surface reconstruction, segregation and diffusion

2021 ◽  
Author(s):  
Yinan Wang ◽  
Linfeng Zhang ◽  
Ben Xu ◽  
Xiaoyang Wang ◽  
Han Wang
Keyword(s):  
Machine Learning ◽  
Surface Properties ◽  
Surface Reconstruction ◽  
First Principles ◽  
Interatomic Potential ◽  
Learning Potential ◽  
Free Surfaces ◽  
Wide Range ◽  
Empirical Force Field ◽  
And Diffusion

Abstract Owing to the excellent catalytic properties of Ag-Au binary nanoalloys, nanostructured Ag-Au, such as Ag-Au nanoparticles and nanopillars, has been under intense investigation. To achieve high accuracy in molecular simulations of Ag-Au nanoalloys, the surface properties must be modeled with first-principles precision. In this work, we constructed a generalizable machine learning interatomic potential for Ag-Au nanoalloys based on deep neural networks trained from a database constructed with first-principles calculations. This potential is highlighted by the accurate prediction of Au (111) surface reconstruction and the segregation of Au toward the Ag-Au nanoalloy surface, where the empirical force field failed in both cases. Moreover, regarding the adsorption and diffusion of adatoms on surfaces, the overall performance of our potential is better than the empirical force fields. We stress that the reported surface properties are blind to the potential modeling in the sense that none of the surface configurations is explicitly included in the training database; therefore, the reported potential is expected to have a strong generalization ability to a wide range of properties and to play a key role in investigating nanostructured Ag-Au evolution, where accurate descriptions of free surfaces are necessary.

Accurate prediction of grain boundary structures and energetics in CdTe: A machine-learning potential approach

2021 ◽  
Author(s):  
Tatsuya Yokoi ◽  
Kosuke Adachi ◽  
Sayuri Iwase ◽  
Katsuyuki Matsunaga
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Grain Boundary ◽  
Interatomic Potential ◽  
Learning Potential ◽  
Potential Approach ◽  
Atomic Structures ◽  
Wide Range ◽  
Artificial Neural Network Ann

To accurately predict grain boundary (GB) atomic structures and their energetics in CdTe, the present study constructs an artificial-neural-network (ANN) interatomic potential. To cover a wide range of atomic environments,...

Electronic and thermal transport in novel carbon-based bilayer with tetragonal rings: a combined study from first-principles and machine learning approach

2021 ◽  
Author(s):  
Supriya Ghosal ◽  
Suman Chowdhury ◽  
Debnarayan Jana
Keyword(s):  
Machine Learning ◽  
First Principles ◽  
Thermal Transport ◽  
Interatomic Potential ◽  
Learning Approach ◽  
First Principles Calculations ◽  
Potential Approach ◽  
Machine Learning Approach ◽  
Tg Structure ◽  
Carbon Based

In this article, the structural, electronic and thermal transport characteristics of bilayer tetragonal graphene (TG) structure are systematically explored combining both first-principles calculations and machine-learning interatomic potential approach. Optimized ground...

Machine learnt bond order potential to model metal–organic (Co–C) heterostructures

Nanoscale ◽  
2017 ◽  
Vol 9 (46) ◽  
pp. 18229-18239 ◽  
Author(s):  
Badri Narayanan ◽  
Henry Chan ◽  
Alper Kinaci ◽  
Fatih G. Sen ◽  
Stephen K. Gray ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
First Principles ◽  
Bond Order ◽  
Interatomic Potential ◽  
Thermodynamic Surface ◽  
Bond Order Potential ◽  
Metal Organic ◽  
Robust Framework

We develop a bond-order based interatomic potential for cobalt–carbon from first-principles data using machine learning. This model accurately captures structural, thermodynamic, surface and mechanical properties of metal–organic heterostructures within a single robust framework.

Combining First-Principles and Data Modeling for the Accurate Prediction of the Refractive Index of Organic Polymers

2017 ◽  
Author(s):  
Mohammad Atif Faiz Afzal ◽  
Chong Cheng ◽  
Johannes Hachmann
Keyword(s):  
First Principles ◽  
Data Modeling ◽  
Accurate Prediction ◽  
Index Of Refraction ◽  
Structure Theory ◽  
Organic Polymers ◽  
Number Density ◽  
Lorenz Equation ◽  
In Silico Studies ◽  
Wide Range

Organic materials with a high index of refraction (RI) are attracting considerable interest due to their potential application in optic and optoelectronic devices. However, most of these applications require an RI value of 1.7 or larger, while typical carbon-based polymers only exhibit values in the range of 1.3–1.5. This paper introduces an efficient computational protocol for the accurate prediction of RI values in polymers to facilitate in silico studies that an guide the discovery and design of next-generation high-RI materials. Our protocol is based on the Lorentz-Lorenz equation and is parametrized by the polarizability and number density values of a given candidate compound. In the proposed scheme, we compute the former using first-principles electronic structure theory and the latter using an approximation based on van der Waals volumes. The critical parameter in the number density approximation is the packing fraction of the bulk polymer, for which we have devised a machine learning model. We demonstrate the performance of the proposed RI protocol by testing its predictions against the experimentally known RI values of 112 optical polymers. Our approach to combine first-principles and data modeling emerges as both a successful and highly economical path to determining the RI values for a wide range of organic polymers.

Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using DFT and Machine Learning

2018 ◽  
Author(s):  
Sherif Tawfik ◽  
Olexandr Isayev ◽  
Catherine Stampfl ◽  
Joseph Shapter ◽  
David Winkler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Band Gap ◽  
Density Functional ◽  
2D Materials ◽  
Van Der Waals ◽  
Building Blocks ◽  
Machine Learning Techniques ◽  
Interlayer Distance ◽  
Computational Screening ◽  
Wide Range

Materials constructed from different van der Waals two-dimensional (2D) heterostructures offer a wide range of benefits, but these systems have been little studied because of their experimental and computational complextiy, and because of the very large number of possible combinations of 2D building blocks. The simulation of the interface between two different 2D materials is computationally challenging due to the lattice mismatch problem, which sometimes necessitates the creation of very large simulation cells for performing density-functional theory (DFT) calculations. Here we use a combination of DFT, linear regression and machine learning techniques in order to rapidly determine the interlayer distance between two different 2D heterostructures that are stacked in a bilayer heterostructure, as well as the band gap of the bilayer. Our work provides an excellent proof of concept by quickly and accurately predicting a structural property (the interlayer distance) and an electronic property (the band gap) for a large number of hybrid 2D materials. This work paves the way for rapid computational screening of the vast parameter space of van der Waals heterostructures to identify new hybrid materials with useful and interesting properties.

Ru Passivated and Ru Doped e-TaN surfaces as Combined Barrier and Liner Material for Copper Interconnects: A First Principles Study

2018 ◽  
Author(s):  
Suresh Natarajan ◽  
Cara-Lena Nies ◽  
Michael Nolan
Keyword(s):  
First Principles ◽  
Film Growth ◽  
Early Stage ◽  
Copper Interconnects ◽  
Liner Material ◽  
Critical Dimensions ◽  
Industry Standard ◽  
Cu Film ◽  
Improved Performance ◽  
And Diffusion

<div>As the critical dimensions of transistors continue to be scaled down to facilitate improved performance and device speeds, new ultrathin materials that combine diffusion barrier and seed/liner properties are needed for copper interconnects at these length scales. Ideally, to facilitate coating of high aspect ratio structures, this alternative barrier+liner material should only consist of one or as few layers as possible. We studied TaN, the current industry standard for Cu diffusion barriers, and Ru, which is a</div><div>suitable liner material for Cu electroplating, to explore how combining these two materials in a barrier+liner material influences the adsorption of Cu atoms in the early stage of Cu film growth. To this end, we carried out first-principles simulations of the adsorption and diffusion of Cu adatoms at Ru-passivated and Ru-doped e-TaN(1 1 0) surfaces. For comparison, we also studied the behaviour of Cu and Ru adatoms at the low index surfaces of e-TaN, as well as the interaction of Cu adatoms with the (0 0 1) surface of hexagonal Ru. Our results confirm the barrier and liner properties of TaN and Ru, respectively while also highlighting the weaknesses of both materials. Ru passivated TaN was found to have improved binding with Cu adatoms as compared to the bare TaN and Ru surfaces.</div><div>On the other hand, the energetic barrier for Cu diffusion at Ru passivated TaN surface was lower than at the bare TaN surface which can promote Cu agglomeration. For Ru-doped TaN however, a decrease in Cu binding energy was found in addition to favourable migration of the Cu adatoms toward the doped Ru atom and unfavourable migration away from it or into the bulk. This suggests that Ru doping sites in the TaN surface can act as nucleation points for Cu growth with high migration barrier preventing agglomeration and allow electroplating of Cu. Therefore Ru-doped TaN is proposed as a candidate for a combined barrier+liner material with reduced thickness.</div>

DOWNHOLE SIGNAL COMPRESSION AND SURFACE RECONSTRUCTION BASED ON DICTIONARY MACHINE LEARNING

2020 ◽  
Author(s):  
Jian Li ◽  
◽  
Bin Dai ◽  
Christopher M. Jones ◽  
Etienne M. Samson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Surface Reconstruction ◽  
Signal Compression

COVID-19 Outbreak Prediction with Machine Learning

2020 ◽  
Author(s):  
Sina Faizollahzadeh Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Control Measures ◽  
Future Research ◽  
Complex Nature ◽  
Inference System ◽  
Wide Range ◽  
Standard Models ◽  
High Level

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to SIR and SEIR models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.

Intelligent Techniques Analysis for Glycosylation Site Prediction

2021 ◽  
Vol 15 ◽  
Author(s):  
Alhassan Alkuhlani ◽  
Walaa Gad ◽  
Mohamed Roushdy ◽  
Abdel-Badeeh M. Salem
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Cell Interaction ◽  
Glycosylation Site ◽  
Machine Learning Classification ◽  
Site Prediction ◽  
Glycosylation Sites ◽  
Wide Range ◽  
Feature Extraction And Selection ◽  
Computational Intelligent

Background: Glycosylation is one of the most common post-translation modifications (PTMs) in organism cells. It plays important roles in several biological processes including cell-cell interaction, protein folding, antigen’s recognition, and immune response. In addition, glycosylation is associated with many human diseases such as cancer, diabetes and coronaviruses. The experimental techniques for identifying glycosylation sites are time-consuming, extensive laboratory work, and expensive. Therefore, computational intelligence techniques are becoming very important for glycosylation site prediction. Objective: This paper is a theoretical discussion of the technical aspects of the biotechnological (e.g., using artificial intelligence and machine learning) to digital bioinformatics research and intelligent biocomputing. The computational intelligent techniques have shown efficient results for predicting N-linked, O-linked and C-linked glycosylation sites. In the last two decades, many studies have been conducted for glycosylation site prediction using these techniques. In this paper, we analyze and compare a wide range of intelligent techniques of these studies from multiple aspects. The current challenges and difficulties facing the software developers and knowledge engineers for predicting glycosylation sites are also included. Method: The comparison between these different studies is introduced including many criteria such as databases, feature extraction and selection, machine learning classification methods, evaluation measures and the performance results. Results and conclusions: Many challenges and problems are presented. Consequently, more efforts are needed to get more accurate prediction models for the three basic types of glycosylation sites.

Sign in / Sign up

Export Citation Format

Share Document