scholarly journals Machine Learning Prediction of Surface Segregation Energies on Low Index Bimetallic Surfaces

Energies ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 2182
Author(s):  
Damilola Ologunagba ◽  
Shyam Kattel
Keyword(s):  
Machine Learning ◽  
Dft Calculations ◽  
Bimetallic Catalysts ◽  
Density Functional ◽  
Surface Segregation ◽  
Surface Composition ◽  
Bulk Composition ◽  
Statistical Machine Learning ◽  
Bimetallic Surfaces ◽  
Computing Platforms

Surface chemical composition of bimetallic catalysts can differ from the bulk composition because of the segregation of the alloy components. Thus, it is very useful to know how the different components are arranged on the surface of catalysts to gain a fundamental understanding of the catalysis occurring on bimetallic surfaces. First-principles density functional theory (DFT) calculations can provide deeper insight into the surface segregation behavior and help understand the surface composition on bimetallic surfaces. However, the DFT calculations are computationally demanding and require large computing platforms. In this regard, statistical/machine learning methods provide a quick and alternative approach to study materials properties. Here, we trained previously reported surface segregation energies on low index surfaces of bimetallic catalysts using various linear and non-linear statistical methods to find a correlation between surface segregation energies and elemental properties. The results revealed that the surface segregation energies on low index bimetallic surfaces can be predicted using fundamental elemental properties.

scholarly journals Data-driven studies of magnetic two-dimensional materials

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Trevor David Rhone ◽  
Wei Chen ◽  
Shaan Desai ◽  
Steven B. Torrisi ◽  
Daniel T. Larson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Dft Calculations ◽  
Density Functional ◽  
Magnetic Coupling ◽  
Magnetic Ordering ◽  
Magnetic Behavior ◽  
Data Driven ◽  
Two Dimensional ◽  
Computationally Efficient ◽  
Data Driven Approach

Abstract We use a data-driven approach to study the magnetic and thermodynamic properties of van der Waals (vdW) layered materials. We investigate monolayers of the form $$\hbox {A}_2\hbox {B}_2\hbox {X}_6$$ A 2 B 2 X 6 , based on the known material $$\hbox {Cr}_2\hbox {Ge}_2\hbox {Te}_6$$ Cr 2 Ge 2 Te 6 , using density functional theory (DFT) calculations and machine learning methods to determine their magnetic properties, such as magnetic order and magnetic moment. We also examine formation energies and use them as a proxy for chemical stability. We show that machine learning tools, combined with DFT calculations, can provide a computationally efficient means to predict properties of such two-dimensional (2D) magnetic materials. Our data analytics approach provides insights into the microscopic origins of magnetic ordering in these systems. For instance, we find that the X site strongly affects the magnetic coupling between neighboring A sites, which drives the magnetic ordering. Our approach opens new ways for rapid discovery of chemically stable vdW materials that exhibit magnetic behavior.

scholarly journals Machine Learning Representation for Atomic Forces and Energies

2020 ◽  
Vol 36 (2) ◽  
Author(s):  
Pham Tien Lam ◽  
Nguyen Van Duy ◽  
Nguyen Tien Cuong
Keyword(s):  
Machine Learning ◽  
Dft Calculations ◽  
Linear Combination ◽  
Density Functional ◽  
Crystalline Silicon ◽  
Basis Functions ◽  
Atomic Energy ◽  
Model Parameters ◽  
Force Model ◽  
L2 Norm

We present machine learning models for fast estimating atomic forces. In our method, the total energy of a system is approximated as the summation of atomic energy which is the interaction energy with its surrounding chemical environment within a certain cutoff radius. Atomic energy is decomposed into two-body terms which are expressed as a linear combination of basis functions. For the force exerted on an atom, we employ a linear combination of a set of basis functions for representing pairwise force. We use least-square linear regression regularized by the l2-norm, known as Ridge regression, to estimate model parameters. We demonstrate that our model can accurately reproduce atomic forces and energies from density-functional-theory (DFT) calculations for crystalline and amorphous silicon. The machine learning force model is then applied to calculate the phonon dispersion of crystalline silicon. The result shows reasonable agreement with DFT calculations.

scholarly journals Convergence Acceleration in Machine Learning Potentials for Atomistic Simulations

2022 ◽  
Author(s):  
Dylan Bayerl ◽  
Christopher Michael Andolina ◽  
Shyam Dwaraknath ◽  
Wissam A Saidi
Keyword(s):  
Machine Learning ◽  
Density Functional Theory ◽  
Dft Calculations ◽  
Density Functional ◽  
Convergence Acceleration ◽  
Atomistic Simulations ◽  
Functional Theory ◽  
Materials Modeling

Machine learning potentials (MLPs) for atomistic simulations have an enormous prospective impact on materials modeling, offering orders of magnitude speedup over density functional theory (DFT) calculations without appreciably sacrificing accuracy...

Thermodynamic Modeling of Surface Segregation in Au-Ti Nanoparticles

2005 ◽  
Vol 23 ◽  
pp. 259-262
Author(s):  
Rengaswamy Jayaganthan ◽  
Gan Moog Chow
Keyword(s):  
Size Effect ◽  
Thermodynamic Modeling ◽  
Thermodynamic Model ◽  
Surface Segregation ◽  
Surface Composition ◽  
Bulk Composition ◽  
Quasichemical Model ◽  
Ti Alloys

The surface composition of nanoparticles is generally different from the average or bulk composition; this phenomenon is commonly referred to as surface segregation. In the present work, the surface segregation in Au-Ti nanoparticles has been analyzed based on a thermodynamic model that incorporates the size effect into the quasichemical model. The calculated surface compositions of Au-Ti nanoparticles are compared with that of the bulk Au-Ti alloys.

scholarly journals Machine learning enabling prediction of the bond dissociation enthalpy of hypervalent iodine from SMILES

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Masaya Nakajima ◽  
Tetsuhiro Nemoto
Keyword(s):  
Machine Learning ◽  
Dft Calculations ◽  
Density Functional ◽  
High Accuracy ◽  
Machine Learning Algorithms ◽  
Hypervalent Iodine ◽  
Bond Dissociation Enthalpy ◽  
Important Indicator ◽  
Bond Dissociation ◽  
Dissociation Enthalpy

AbstractMachine learning to create models on the basis of big data enables predictions from new input data. Many tasks formerly performed by humans can now be achieved by machine learning algorithms in various fields, including scientific areas. Hypervalent iodine compounds (HVIs) have long been applied as useful reactive molecules. The bond dissociation enthalpy (BDE) value is an important indicator of reactivity and stability. Experimentally measuring the BDE value of HVIs is difficult, however, and the value has been estimated by quantum calculations, especially density functional theory (DFT) calculations. Although DFT calculations can access the BDE value with high accuracy, the process is highly time-consuming. Thus, we aimed to reduce the time for predicting the BDE by applying machine learning. We calculated the BDE of more than 1000 HVIs using DFT calculations, and performed machine learning. Converting SMILES strings to Avalon fingerprints and learning using a traditional Elastic Net made it possible to predict the BDE value with high accuracy. Furthermore, an applicability domain search revealed that the learning model could accurately predict the BDE even for uncovered inputs that were not completely included in the training data.

Predicting displacements of octahedral cations in ferroelectric perovskites using machine learning

2017 ◽  
Vol 73 (5) ◽  
pp. 962-967 ◽  
Author(s):  
Prasanna V. Balachandran ◽  
Toby Shearman ◽  
James Theiler ◽  
Turab Lookman
Keyword(s):  
Machine Learning ◽  
Dft Calculations ◽  
Density Functional ◽  
Ferroelectric Properties ◽  
Relative Magnitude ◽  
High Symmetry ◽  
Functional Theory ◽  
Octahedral Cation ◽  
Pauling Electronegativity ◽  
Octahedral Cations

In ferroelectric perovskites, displacements of cations from the high-symmetry lattice positions in the paraelectric phase break the spatial inversion symmetry. Furthermore, the relative magnitude of ionic displacements correlate strongly with ferroelectric properties such as the Curie temperature. As a result, there is interest in predicting the relative displacements of cations prior to experiments. Here, machine learning is used to predict the average displacement of octahedral cations from its high-symmetry position in ferroelectric perovskites. Published octahedral cation displacements data from density functional theory (DFT) calculations are used to train machine learning models, where each cation is represented by features such as Pauling electronegativity, Martynov–Batsanov electronegativity and the ratio of valence electron number to nominal charge. Average displacements for ten new octahedral cations for which DFT data do not exist are predicted. Predictions are validated by comparing them with new DFT calculations and existing experimental data. The outcome of this work has implications in the design and discovery of novel ferroelectric perovskites.

scholarly journals Automated Detection and Characterization of Surface Restructuring Events in Bimetallic Catalysts

2019 ◽  
Author(s):  
Jin Soo Lim ◽  
Nicola Molinari ◽  
Kaining Duanmu ◽  
Philippe Sautet ◽  
Boris Kozinsky
Keyword(s):  
Bimetallic Catalysts ◽  
Density Functional ◽  
Surface Segregation ◽  
Surface Restructuring ◽  
Bimetallic Systems ◽  
Automated Method ◽  
Elementary Surface ◽  
Systematic Understanding ◽  
Interlayer Exchange

<div>Surface restructuring in bimetallic systems has recently been shown to play a crucial role in heterogeneous catalysis. In particular, the segregation in binary alloys can be reversed in the presence of strongly bound adsorbates. Mechanistic characterization of such restructuring phenomena at the atomic level remains scarce and challenging due to the large configurational space that must be explored. To this end, we propose an automated method to discover elementary surface restructuring processes in an unbiased fashion, using Pd/Ag as an example. We employ high-temperature classical molecular dynamics (MD) to rapidly detect restructuring events, isolate them, and optimize using density functional theory (DFT). In addition to confirming the known exchange descent mechanism, our systematic approach has revealed three new predominant classes of events at step edges of close-packed surfaces that have not been considered before: (1) vacancy insertion; (2) direct exchange; (3) interlayer exchange. The discovered events enable us to construct the complete set of mechanistic pathways by which Pd is incorporated into the Ag host in vacuum. These atomistic insights provide a step toward systematic understanding and engineering of surface segregation dynamics in bimetallic catalysts.</div>

scholarly journals Multi-fidelity Statistical Machine Learning for Molecular Crystal Structure Prediction

2020 ◽  
Author(s):  
Olga Egorova ◽  
Roohollah Hafizi ◽  
David C. Woods ◽  
Graeme Day
Keyword(s):  
Crystal Structure ◽  
Machine Learning ◽  
Force Field ◽  
Crystal Structures ◽  
Structure Prediction ◽  
Density Functional ◽  
Region Of Interest ◽  
State Density ◽  
Statistical Machine Learning ◽  
Hybrid Functional

The prediction of crystal structures from first principles requires highly accurate energies for large numbers of putative crystal structures. The accuracy of solid state density functional theory (DFT) calculations is often required, but hundreds or more structures can be present in the low energy region of interest, so that the associated computational costs are prohibitive. Here, we apply statistical machine learning to predict expensive hybrid functional DFT (PBE0) calculations using a multi-fidelity approach to re-evalute the energies of crystal structures predicted with an inexpensive force field. The method uses an autoregressive Gaussian process, making use of less expensive GGA DFT (PBE) calculations to bridge the gap between the force field and PBE0 energies. The method is benchmarked on the crystal structure landscapes of three small, hydrogen bonding organic molecules and shown to produce accurate predictions of energies and crystal structure ranking using small numbers of the most expensive calculations; the PBE0 energies can be predicted with errors of less than 1 kJ/mol with between 4.2-6.8% of the cost of the full calculations. As the model that we have developed is probabilistic, we discuss how the uncertainties in predicted energies impact on assessment of the energetic ranking of crystal structures.

In-Situ Surface Composition Measurements of CuGaSe2 Thin Films

1997 ◽  
Vol 485 ◽  
Author(s):  
P. Fons ◽  
A. Yamada ◽  
S. Niki ◽  
H. Oyanagi
Keyword(s):  
Surface Segregation ◽  
Surface Composition ◽  
Bulk Composition ◽  
High Sensitivity ◽  
Film Structure ◽  
High Concentration ◽  
Force Microscopy ◽  
Atomic Force ◽  
Voltage Dependent ◽  
Composition Measurements

AbstractTwo CuGaSe2 films were grown by molecular beam epitaxy onto GaAs (001) substrates with varying Cu/Ga flux ratios under Se overpressure conditions. Growth was interrupted at predetermined times and the surface composition was measured using Auger electron spectroscopy after which growth was continued. After growth, the film composition was analyzed using voltage dependent electron microprobe spectroscopy. Film structure and morphology were also analyzed using x-ray diffraction and atomic force microscopy. The film with a Cu/Ga ratio larger than unity showed evidence of surface segregation of a second Cu-rich phase with a Cu/Se composition ratio slightly greater than unity. A second CuGaSe2 film with a Cu/Ga ratio of less than unity showed no change in surface composition with time and was also consistent with bulk composition measurements. Diffraction measurements indicated a high concentration of twins as well as the presence of domains with mixed c and a axes in the Ga-rich film. The Cu-rich films by contrast were single domain and had a narrower mosaics. High sensitivity scans along the [001] reciprocal axis did not exhibit any new peaks not attributable to either the substrate or the CuGaSe2 thin film.

Sign in / Sign up

Export Citation Format

Share Document