scholarly journals Bandgap prediction of two-dimensional materials using machine learning

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0255637
Author(s):  
Yu Zhang ◽  
Wenjing Xu ◽  
Guangjie Liu ◽  
Zhiyong Zhang ◽  
Jinlong Zhu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Semiconductor Device ◽  
2D Materials ◽  
Support Vector ◽  
Material Structure ◽  
Two Dimensional ◽  
Promising Alternative ◽  
Two Dimensional Materials ◽  
Device Applications ◽  
Boosted Decision Trees

The bandgap of two-dimensional (2D) materials plays an important role in their applications to various devices. For instance, the gapless nature of graphene limits the use of this material to semiconductor device applications, whereas the indirect bandgap of molybdenum disulfide is suitable for electrical and photo-device applications. Therefore, predicting the bandgap rapidly and accurately for a given 2D material structure has great scientific significance in the manufacturing of semiconductor devices. Compared to the extremely high computation cost of conventional first-principles calculations, machine learning (ML) based on statistics may be a promising alternative to predicting bandgaps. Although ML algorithms have been used to predict the properties of materials, they have rarely been used to predict the properties of 2D materials. In this study, we apply four ML algorithms to predict the bandgaps of 2D materials based on the computational 2D materials database (C2DB). Gradient boosted decision trees and random forests are more effective in predicting bandgaps of 2D materials with an R2 >90% and root-mean-square error (RMSE) of ~0.24 eV and 0.27 eV, respectively. By contrast, support vector regression and multi-layer perceptron show that R2 is >70% with RMSE of ~0.41 eV and 0.43 eV, respectively. Finally, when the bandgap calculated without spin-orbit coupling (SOC) is used as a feature, the RMSEs of the four ML models decrease greatly to 0.09 eV, 0.10 eV, 0.17 eV, and 0.12 eV, respectively. The R2 of all the models is >94%. These results show that the properties of 2D materials can be rapidly obtained by ML prediction with high precision.

Quantifying the CVD-Grown Two-Dimensional Materials via Image Clustering

Nanoscale ◽  
2021 ◽  
Author(s):  
Zebin Li ◽  
Jihea Lee ◽  
Fei Yao ◽  
Hongyue Sun
Keyword(s):  
Machine Learning ◽  
Chemical Vapor Deposition ◽  
Vapor Deposition ◽  
2D Materials ◽  
Chemical Vapor ◽  
Image Clustering ◽  
Two Dimensional ◽  
Two Dimensional Materials

Machine learning (ML) techniques have been recently employed to facilitate the development of novel two-dimensional (2D) materials. Among various synthesis approaches, chemical vapor deposition (CVD) has demonstrated tremendous potential in...

scholarly journals Recent advances in mode-locked fiber lasers based on two-dimensional materials

Nanophotonics ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 2315-2340 ◽  
Author(s):  
Junli Wang ◽  
Xiaoli Wang ◽  
Jingjing Lei ◽  
Mengyuan Ma ◽  
Cong Wang ◽  
...  
Keyword(s):  
Fiber Lasers ◽  
2D Materials ◽  
Synthesis Methods ◽  
Two Dimensional ◽  
New Materials ◽  
Saturable Absorbers ◽  
Operating Wavelength ◽  
Recent Advances ◽  
Two Dimensional Materials ◽  
Diverse Mode

AbstractDue to the unique properties of two-dimensional (2D) materials, much attention has been paid to the exploration and application of 2D materials. In this review, we focus on the application of 2D materials in mode-locked fiber lasers. We summarize the synthesis methods for 2D materials, fiber integration with 2D materials and 2D materials based saturable absorbers. We discuss the performance of the diverse mode-locked fiber lasers in the typical operating wavelength such as 1, 1.5, 2 and 3 μm. Finally, a summary and outlook of the further applications of the new materials in mode-locked fiber lasers are presented.

scholarly journals A Universal Atomic Substitution Conversion Strategy Towards Synthesis of Large-Size Ultrathin Nonlayered Two-Dimensional Materials

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Mei Zhao ◽  
Sijie Yang ◽  
Kenan Zhang ◽  
Lijie Zhang ◽  
Ping Chen ◽  
...  
Keyword(s):  
Theoretical Calculations ◽  
2D Materials ◽  
Direct Synthesis ◽  
Two Dimensional ◽  
Covalent Bonds ◽  
2D Layered Materials ◽  
Large Size ◽  
Two Dimensional Materials ◽  
Microfabrication Technique ◽  
Atomic Substitution

AbstractNonlayered two-dimensional (2D) materials have attracted increasing attention, due to novel physical properties, unique surface structure, and high compatibility with microfabrication technique. However, owing to the inherent strong covalent bonds, the direct synthesis of 2D planar structure from nonlayered materials, especially for the realization of large-size ultrathin 2D nonlayered materials, is still a huge challenge. Here, a general atomic substitution conversion strategy is proposed to synthesize large-size, ultrathin nonlayered 2D materials. Taking nonlayered CdS as a typical example, large-size ultrathin nonlayered CdS single-crystalline flakes are successfully achieved via a facile low-temperature chemical sulfurization method, where pre-grown layered CdI2 flakes are employed as the precursor via a simple hot plate assisted vertical vapor deposition method. The size and thickness of CdS flakes can be controlled by the CdI2 precursor. The growth mechanism is ascribed to the chemical substitution reaction from I to S atoms between CdI2 and CdS, which has been evidenced by experiments and theoretical calculations. The atomic substitution conversion strategy demonstrates that the existing 2D layered materials can serve as the precursor for difficult-to-synthesize nonlayered 2D materials, providing a bridge between layered and nonlayered materials, meanwhile realizing the fabrication of large-size ultrathin nonlayered 2D materials.

Molecular Functionalization of 2D-Materials: From Atomically Planar 2D Architectures to Off-Plane 3D Functional Materials

2021 ◽  
Author(s):  
Adam Brill ◽  
Elad Koren ◽  
Graham de Ruiter
Keyword(s):  
2D Materials ◽  
Functional Materials ◽  
Two Dimensional ◽  
The Past ◽  
Two Dimensional Materials

Atomically thin two-dimensional materials (2DMs) have moved in the past 15 years from a serendipitously isolated single-layered graphene curiosity to a near technological renaissance, where 2DMs such as graphene and...

scholarly journals Developing a Process for the Analysis of User Journeys and the Prediction of Dropout in Digital Health Interventions: Machine Learning Approach (Preprint)

2020 ◽  
Author(s):  
Vincent Bremer ◽  
Philip I Chow ◽  
Burkhardt Funk ◽  
Frances P Thorndike ◽  
Lee M Ritterband
Keyword(s):  
Machine Learning ◽  
Decision Trees ◽  
Behavioral Therapy ◽  
Digital Health ◽  
Area Under The Curve ◽  
Prediction Performance ◽  
Health Interventions ◽  
Drop Out ◽  
Support Vector ◽  
Boosted Decision Trees

BACKGROUND User dropout is a widespread concern in the delivery and evaluation of digital (ie, web and mobile apps) health interventions. Researchers have yet to fully realize the potential of the large amount of data generated by these technology-based programs. Of particular interest is the ability to predict who will drop out of an intervention. This may be possible through the analysis of user journey data—self-reported as well as system-generated data—produced by the path (or journey) an individual takes to navigate through a digital health intervention. OBJECTIVE The purpose of this study is to provide a step-by-step process for the analysis of user journey data and eventually to predict dropout in the context of digital health interventions. The process is applied to data from an internet-based intervention for insomnia as a way to illustrate its use. The completion of the program is contingent upon completing 7 sequential cores, which include an initial tutorial core. Dropout is defined as not completing the seventh core. METHODS Steps of user journey analysis, including data transformation, feature engineering, and statistical model analysis and evaluation, are presented. Dropouts were predicted based on data from 151 participants from a fully automated web-based program (Sleep Healthy Using the Internet) that delivers cognitive behavioral therapy for insomnia. Logistic regression with L1 and L2 regularization, support vector machines, and boosted decision trees were used and evaluated based on their predictive performance. Relevant features from the data are reported that predict user dropout. RESULTS Accuracy of predicting dropout (area under the curve [AUC] values) varied depending on the program core and the machine learning technique. After model evaluation, boosted decision trees achieved AUC values ranging between 0.6 and 0.9. Additional handcrafted features, including time to complete certain steps of the intervention, time to get out of bed, and days since the last interaction with the system, contributed to the prediction performance. CONCLUSIONS The results support the feasibility and potential of analyzing user journey data to predict dropout. Theory-driven handcrafted features increased the prediction performance. The ability to predict dropout at an individual level could be used to enhance decision making for researchers and clinicians as well as inform dynamic intervention regimens.

scholarly journals Different Machine Learning Classifiers for Music Emotion Recognition

2019 ◽  
Vol 8 (4) ◽  
pp. 2187-2191
Keyword(s):  
Machine Learning ◽  
Emotion Recognition ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
Bayes Classifier ◽  
Promising Alternative ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Statistical Metrics

Music in an essential part of life and the emotion carried by it is key to its perception and usage. Music Emotion Recognition (MER) is the task of identifying the emotion in musical tracks and classifying them accordingly. The objective of this research paper is to check the effectiveness of popular machine learning classifiers like XGboost, Random Forest, Decision Trees, Support Vector Machine (SVM), K-Nearest-Neighbour (KNN) and Gaussian Naive Bayes on the task of MER. Using the MIREX-like dataset [17] to test these classifiers, the effects of oversampling algorithms like Synthetic Minority Oversampling Technique (SMOTE) [22] and Random Oversampling (ROS) were also verified. In all, the Gaussian Naive Bayes classifier gave the maximum accuracy of 40.33%. The other classifiers gave accuracies in between 20.44% and 38.67%. Thus, a limit on the classification accuracy has been reached using these classifiers and also using traditional musical or statistical metrics derived from the music as input features. In view of this, deep learning-based approaches using Convolutional Neural Networks (CNNs) [13] and spectrograms of the music clips for MER is a promising alternative.

Preparation of single-crystal metal substrates for the growth of high-quality two-dimensional materials

2021 ◽  
Vol 8 (1) ◽  
pp. 182-200
Author(s):  
Yanglizhi Li ◽  
Luzhao Sun ◽  
Haiyang Liu ◽  
Yuechen Wang ◽  
Zhongfan Liu
Keyword(s):  
Single Crystal ◽  
2D Materials ◽  
Controlled Growth ◽  
Two Dimensional ◽  
High Quality ◽  
Metal Substrates ◽  
Recent Advances ◽  
Two Dimensional Materials

Recent advances on preparing single-crystal metals and their crucial roles in controlled growth of high-quality 2D materials are reviewed.

2D materials towards ultrafast photonic applications

2020 ◽  
Vol 22 (39) ◽  
pp. 22140-22156
Author(s):  
Xin-Ping Zhai ◽  
Bo Ma ◽  
Qiang Wang ◽  
Hao-Li Zhang
Keyword(s):  
Optical Communications ◽  
2D Materials ◽  
Optical Limiting ◽  
Mode Locking ◽  
Optical Devices ◽  
Optical Modulation ◽  
Two Dimensional ◽  
Two Dimensional Materials ◽  
All Optical ◽  
Ultrafast Photonics

Two-dimensional materials are now excelling in yet another arena of ultrafast photonics, including optical modulation through optical limiting/mode-locking, photodetectors, optical communications, integrated miniaturized all-optical devices, etc.

scholarly journals Energy loss by fast-travelling charged particles traversing two-dimensional materials

2020 ◽  
Vol 233 ◽  
pp. 03005
Author(s):  
Jaime E. Santos ◽  
Mikhail Vasilevskiy ◽  
Nuno M.R. Peres ◽  
Antti-Pekka Jauho
Keyword(s):  
Thin Films ◽  
Energy Loss ◽  
2D Materials ◽  
Charged Particles ◽  
Monolayer Graphene ◽  
Two Dimensional ◽  
Particle Detection ◽  
Hydrodynamic Approximation ◽  
Radiation Losses ◽  
Two Dimensional Materials

We consider the problem of the radiation losses by fast-traveling particles traversing two-dimensional (2d) materials or thin films. After review¬ing the screening of electromagnetic fields by two dimensional conducting ma¬terials, we obtain the energy loss by a fast particle traversing such a material or film. In particular, we discuss the pattern of radiation emitted by monolayer graphene treated within a hydrodynamic approximation. These results are com¬pared with recent published results using similar approximations and, having in mind a potential application to particle detection, we briefly discuss how one can improve on the signals obtained by using other two-dimensional materials.

Fabrication of a three-terminal graphene nanoelectromechanical switch using two-dimensional materials

Nanoscale ◽  
2018 ◽  
Vol 10 (26) ◽  
pp. 12349-12355 ◽  
Author(s):  
Ngoc Huynh Van ◽  
Manoharan Muruganathan ◽  
Jothiramalingam Kulothungan ◽  
Hiroshi Mizuta
Keyword(s):  
Leakage Current ◽  
2D Materials ◽  
Two Dimensional ◽  
Subthreshold Slope ◽  
Drive Current ◽  
Exponential Increase ◽  
Two Dimensional Materials

An all-2D materials three-terminal subthermal subthreshold slope nanoelectromechanical (NEM) switch is realized to overcome the exponential increase in leakage current with an increase in the drive current of CMOS devices.

Sign in / Sign up

Export Citation Format

Share Document