An efficient rule-based screening approach for discovering fast lithium ion conductors using density functional theory and artificial neural networks

2014 ◽  
Vol 2 (3) ◽  
pp. 720-734 ◽  
Author(s):  
Randy Jalem ◽  
Masanobu Nakayama ◽  
Toshihiro Kasuga
Keyword(s):  
Neural Networks ◽  
Density Functional Theory ◽  
Artificial Neural Networks ◽  
Density Functional ◽  
Lithium Ion ◽  
Functional Theory ◽  
Rule Based ◽  
Screening Approach ◽  
Artificial Neural ◽  
Lithium Ion Conductors

scholarly journals Accelerated Modeling of Lithium Diffusion in Solid State Electrolytes Using Artificial Neural Networks

2020 ◽  
Author(s):  
Karun Kumar Rao ◽  
Yan Yao ◽  
Lars Grabow
Keyword(s):  
Neural Networks ◽  
Molecular Dynamics ◽  
Artificial Neural Networks ◽  
Solid State ◽  
Ab Initio ◽  
Density Functional ◽  
Lithium Ion ◽  
Md Simulations ◽  
High Accuracy ◽  
Artificial Neural

There is great interest in solid state lithium electrolytes to replace the flammable organic electrolyte for an all solid state battery. Previous efforts trying to understand the structure-function relationships resulting in high ionic conductivity materials have mainly relied on <i>ab initio</i> molecular dynamics. Such simulations, however, are computationally demanding and cannot be reasonably applied to large systems containing more than a few hundred atoms. Herein, we investigate using artificial neural networks (ANN) to accelerate the calculation of high accuracy atomic forces and energies used during molecular dynamics (MD) simulations, to eliminate the need for costly <i>ab initio </i>force and energy evaluation methods, such as density functional theory (DFT). After carefully training a robust ANN for four and five element systems, we obtain nearly identical lithium ion diffusivities for Li<sub>10</sub>GeP<sub>2</sub>S<sub>12</sub> (LGPS) when benchmarking the ANN-MD results with DFT-MD. To demonstrate the power of the outlined ANN-MD approach we apply it to a doped LGPS system to calculate the effect of concentrations of chlorine on the lithium diffusivity at a resolution that would be unrealistic to model with DFT-MD. We find that ANN-MD simulations can provide the framework to study systems that require a large number of atoms more efficiently while maintaining high accuracy.

scholarly journals Accelerated Modeling of Lithium Diffusion in Solid State Electrolytes Using Artificial Neural Networks

2020 ◽  
Author(s):  
Karun Kumar Rao ◽  
Yan Yao ◽  
Lars Grabow
Keyword(s):  
Neural Networks ◽  
Molecular Dynamics ◽  
Artificial Neural Networks ◽  
Solid State ◽  
Ab Initio ◽  
Density Functional ◽  
Lithium Ion ◽  
Md Simulations ◽  
High Accuracy ◽  
Artificial Neural

There is great interest in solid state lithium electrolytes to replace the flammable organic electrolyte for an all solid state battery. Previous efforts trying to understand the structure-function relationships resulting in high ionic conductivity materials have mainly relied on <i>ab initio</i> molecular dynamics. Such simulations, however, are computationally demanding and cannot be reasonably applied to large systems containing more than a few hundred atoms. Herein, we investigate using artificial neural networks (ANN) to accelerate the calculation of high accuracy atomic forces and energies used during molecular dynamics (MD) simulations, to eliminate the need for costly <i>ab initio </i>force and energy evaluation methods, such as density functional theory (DFT). After carefully training a robust ANN for four and five element systems, we obtain nearly identical lithium ion diffusivities for Li<sub>10</sub>GeP<sub>2</sub>S<sub>12</sub> (LGPS) when benchmarking the ANN-MD results with DFT-MD. To demonstrate the power of the outlined ANN-MD approach we apply it to a doped LGPS system to calculate the effect of concentrations of chlorine on the lithium diffusivity at a resolution that would be unrealistic to model with DFT-MD. We find that ANN-MD simulations can provide the framework to study systems that require a large number of atoms more efficiently while maintaining high accuracy.

scholarly journals Transformer-based artificial neural networks for the conversion between chemical notations

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Lev Krasnov ◽  
Ivan Khokhlov ◽  
Maxim V. Fedorov ◽  
Sergey Sosnin
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Rapid Development ◽  
Performance Level ◽  
Rule Based ◽  
Development Costs ◽  
Overall Performance ◽  
Artificial Neural

AbstractWe developed a Transformer-based artificial neural approach to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct. The overall performance level of our model is comparable to the rule-based solutions. We proved that the accuracy and speed of computations as well as the robustness of the model allow to use it in production. Our showcase demonstrates that a neural-based solution can facilitate rapid development keeping the required level of accuracy. We believe that our findings will inspire other developers to reduce development costs by replacing complex rule-based solutions with neural-based ones.

scholarly journals Predicting the new carbon nanocages, fullerynes: a DFT study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mohammad Qasemnazhand ◽  
Farhad Khoeini ◽  
Farah Marsusi
Keyword(s):  
Density Functional Theory ◽  
Lithium Ion Batteries ◽  
Density Functional ◽  
Lithium Ion ◽  
The Other ◽  
Electron Affinities ◽  
Chemical Formula ◽  
Functional Theory ◽  
Triple Bonds ◽  
Structural And Electronic Properties

AbstractIn this study, based on density functional theory, we propose a new branch of pseudo-fullerenes which contain triple bonds with sp hybridization. We call these new nanostructures fullerynes, according to IUPAC. We present four samples with the chemical formula of C4nHn, and the structures derived from fulleranes. We compare the structural and electronic properties of these structures with those of two common fullerenes and fulleranes systems. The calculated electron affinities of the sampled fullerynes are negative, and much smaller than those of fullerenes, so they should be chemically more stable than fullerenes. Although fulleranes also exhibit higher chemical stability than fullerynes, but pentagon or hexagon of the fullerane structures cannot pass ions and molecules. Applications of fullerynes can be included in the storage of ions and gases at the nanoscale. On the other hand, they can also be used as cathode/anode electrodes in lithium-ion batteries.

Sign in / Sign up

Export Citation Format

Share Document