2020
DOI: 10.1039/d0ra02943b
|View full text |Cite
|
Sign up to set email alerts
|

Bandgaps of noble and transition metal/ZIF-8 electro/catalysts: a computational study

Abstract: Band gap estimation for metal/ZIF-8 framework electro/catalysts by hybrid DFT and machine learning technique.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
13
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8

Relationship

3
5

Authors

Journals

citations
Cited by 20 publications
(14 citation statements)
references
References 64 publications
1
13
0
Order By: Relevance
“…Instead of searching a hyperplane, where the distance to the closest data points is maximized, the distance between the SVR hyperplane and most data points is no more than the tolerance margin, ξ, with ξ being determined by the required accuracy of the model. Both SVC and SVR can be used for catalytic activity prediction and simplification of DFT calculations. , For example, Baghban et al shortened the DFT calculation time for determining the bandgap of zeolitic imidazolate frameworks (ZIFs) using an SVM model, providing a simple approach for the design of ZIF-based electrocatalysts …”
Section: Machine Learning Modelingmentioning
confidence: 99%
See 1 more Smart Citation
“…Instead of searching a hyperplane, where the distance to the closest data points is maximized, the distance between the SVR hyperplane and most data points is no more than the tolerance margin, ξ, with ξ being determined by the required accuracy of the model. Both SVC and SVR can be used for catalytic activity prediction and simplification of DFT calculations. , For example, Baghban et al shortened the DFT calculation time for determining the bandgap of zeolitic imidazolate frameworks (ZIFs) using an SVM model, providing a simple approach for the design of ZIF-based electrocatalysts …”
Section: Machine Learning Modelingmentioning
confidence: 99%
“…87,187−190 For example, Baghban et al shortened the DFT calculation time for determining the bandgap of zeolitic imidazolate frameworks (ZIFs) using an SVM model, providing a simple approach for the design of ZIF-based electrocatalysts. 191 The SVM, a nonlinear algorithm, provides a global solution to the feature−property relation, shows good generation ability, and is insensitive to outliers. Nevertheless, training of the SVM model is very slow on a large data set, and there is no general rule for the selection of kernel functions.…”
Section: Support Vector Machinesmentioning
confidence: 99%
“…Moreover, machine learning approaches have recently been applied in different areas such as chemistry, catalyst, energy, chemical processes, etc. 44 49 . Support vector machine (SVM) 50 , artificial neural network (ANN) 51 , 52 , fuzzy logic system (FLS) 53 , and adaptive neuro-fuzzy inference system (ANFIS) 54 , 55 are the most familiar categories of machine learning which can be optimized by different optimization algorithms such as particle swarm optimization (PSO) 48 , genetic algorithm (GA) 56 , gray wolf optimization (GWO) 46 , imperialist competitive algorithm (ICA) 57 , teaching learning-based optimization (TLBO) 58 , etc.…”
Section: Introductionmentioning
confidence: 99%
“…26,27 Recently, several chemical engineering problems have been widely studied by ML methods. [28][29][30][31][32][33][34] In 2018, the inuence of several parameters (specic surface area, I D /I G ratio, calculated pore size, doping element, and voltage window) on the capacitance was studied via an articial neutron network (ANN) method. 35 Recently Su et al investigated the effect of porous carbon-based materials and working potential ranges on EDL capacitance by using various ML models.…”
Section: Introductionmentioning
confidence: 99%