Machine Learning Prediction of the Exfoliation Energies of Two-Dimension Materials via Data-Driven Approach

Wan, Zhongyu; Wang, Quan‐De

doi:10.1021/acs.jpclett.1c03335

Cited by 8 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a variety of ML models and some basic physical descriptors, Wan et al. predicted the exfoliation energies of 2D materials and demonstrated the effectiveness of the ensemble tree (ET) model in doing so [34] . A broad machine learning technique recently created by Victor et al., based on graph neural networks, predicts the DOS solely from atomic positions [35] .…”

Section: Introductionmentioning

confidence: 99%

Structural and Electronic Properties of Two‐Dimensional Materials: A Machine‐Learning‐Guided Prediction

Ramanathan,

Chowdhury

2023

ChemPhysChem

View full text Add to dashboard Cite

The growing amount of study and interest in two‐dimensional (2D) materials has not yet resulted in a wide range of material applications. This is a result of the difficulties in getting properties, which are often determined through experimental computations or through first‐principles predictions, both of which require a lot of time and resources. Here, we provide a general machine learning (ML) model that works incredibly well as a predictor for a variety of electronic and structural properties such as band gap, fermi level, work function, total energy and area of unit cell of a wide range of 2D materials derived from the Computational 2D Materials Database (C2DB). Not only that our predicted model for classification of samples works extraordinarily well and gives an accuracy of around 99% for classification. We are able to successfully decrease the number of features by employing a strict permutation‐based feature selection method along with the sure independence screening and sparsifying operator (SISSO) which further supports the design recommendations for the identification of novel 2D materials with the desired properties.

show abstract

Section: Introductionmentioning

confidence: 99%

Structural and Electronic Properties of Two‐Dimensional Materials: A Machine‐Learning‐Guided Prediction

Ramanathan,

Chowdhury

2023

ChemPhysChem

View full text Add to dashboard Cite

show abstract

“…The results showed that generative ML provided excellent approaches to discovering chemicals and new materials. Despite several work filed on 2D materials and computational learning for examples, − reports on the use of new generation AI models for the recovery of value-added precious metals from brine using crown-passivated 2D nanosheets are still lacking. We thus proposed an integration of different disciplines of materials science, nanotechnology, chemistry, dynamic simulation, and ML for the recovery of brine resources, which when implemented shall provide alternative highly efficient, economical, and environmentally friendly approach to BRR.…”

Section: Introductionmentioning

confidence: 99%

Recovery of Brine Resources Through Crown-Passivated Graphene, Silicene, and Boron Nitride Nanosheets Based on Machine-Learning Structural Predictions

Abdulazeez,

Abba,

Usman

et al. 2023

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

“…29 Siriwardane et al 30 developed energy−structure correlation using density functional theory (DFT) and ML to reveal the exfoliation energy of MAB (where M is a transition metal, A is a group 13−16 element, and B is boron) phases. Also based on DFT data, Wan et al 31 used an ML method to accurately predict the exfoliation energies for various 2D materials. It should be noted that the data in Siriwardane et al 30 and Wan et al 31 were from DFT simulations, which did not involve any solvents.…”

Section: Introductionmentioning

confidence: 99%

“…Also based on DFT data, Wan et al 31 used an ML method to accurately predict the exfoliation energies for various 2D materials. It should be noted that the data in Siriwardane et al 30 and Wan et al 31 were from DFT simulations, which did not involve any solvents. In this work, we utilized MD simulations to create a data set for ΔG exf and ΔG sol of g-C 3 N 4 in 49 solvents (water and 48 organic solvents), totaling 31 μs of simulation time.…”

Section: Introductionmentioning

confidence: 99%

Predicting Free Energies of Exfoliation and Solvation for Graphitic Carbon Nitrides Using Machine Learning

Shahini,

Chaulagain,

Shankar

et al. 2023

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

As a metal-free and visible-light-responsive photocatalyst, graphitic carbon nitride (g-C 3 N 4 ) has emerged as a new research hotspot and has attracted broad attention in the field of solar energy conversion and thin-film transistors. Liquid-phase exfoliation (LPE) is the best-known method for the synthesis of 2D g-C 3 N 4 nanosheets. In LPE, bulk g-C 3 N 4 is exfoliated in a solvent via high-shear mixing or sonication in order to produce a stable suspension of individual nanosheets. Two parameters of importance in gauging the performance of a solvent in LPE are the free energy required to exfoliate a unit area of layered materials into individual sheets in the solvent (ΔG exf ) and the solvation free energy per unit area of a nanosheet (ΔG sol ). While approximations for the free energies exist, they are shown in our previous work to be inaccurate and incapable of capturing the experimentally observed efficacy of LPE. Molecular dynamics (MD) simulations can provide accurate free-energy calculations, but doing so for every single solvent is time-and resource-consuming. Herein, machine learning (ML) algorithms are used to predict ΔG exf and ΔG sol for g-C 3 N 4 . First, a database for ΔG exf and ΔG sol is created based on a series of MD simulations involving 49 different solvents with distinct chemical structures and properties. The data set also includes values of critical descriptors for the solvents, including density, surface tension, dielectric constant, etc. Different ML methods are compared, accompanied by descriptor selection, to develop the most accurate model for predicting ΔG exf and ΔG sol . The extra tree regressor is shown to be the best performer among the six ML methods studied. Experimental validation of the model is conducted by performing dispersibility tests in several solvents for which the free energies are predicted. Finally, the influence of the selected descriptors on the free energies is analyzed, and strategies for solvent selection in LPE are proposed.

show abstract

Machine Learning Prediction of the Exfoliation Energies of Two-Dimension Materials via Data-Driven Approach

Cited by 8 publications

References 39 publications

Structural and Electronic Properties of Two‐Dimensional Materials: A Machine‐Learning‐Guided Prediction

Structural and Electronic Properties of Two‐Dimensional Materials: A Machine‐Learning‐Guided Prediction

Recovery of Brine Resources Through Crown-Passivated Graphene, Silicene, and Boron Nitride Nanosheets Based on Machine-Learning Structural Predictions

Predicting Free Energies of Exfoliation and Solvation for Graphitic Carbon Nitrides Using Machine Learning

Contact Info

Product

Resources

About