Active Learning in Bayesian Neural Networks for Bandgap Predictions of Novel Van der Waals Heterostructures

The bandgap is one of the most fundamental properties of condensed matter. However, an accurate calculation of its value, which could potentially allow experimentalists to identify materials suitable for device applications, is very computationally expensive. Here, active machine learning algorithms...

Full description

Saved in:
Bibliographic Details
Published in:Advanced intelligent systems 2021-11, Vol.3 (11), p.n/a
Main Authors: Fronzi, Marco, Isayev, Olexandr, Winkler, David A., Shapter, Joseph G., Ellis, Amanda V., Sherrell, Peter C., Shepelin, Nick A., Corletto, Alexander, Ford, Michael J.
Format: Article
Language:English
Subjects:
2D heterostructures
Accuracy
Active learning
Algorithms
Approximation
bandgaps
bilayers
Density functional theory
Energy gap
Heterostructures
Machine learning
Mathematical analysis
Neural networks
Standard deviation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The bandgap is one of the most fundamental properties of condensed matter. However, an accurate calculation of its value, which could potentially allow experimentalists to identify materials suitable for device applications, is very computationally expensive. Here, active machine learning algorithms are used to leverage a limited number of accurate density functional theory calculations to robustly predict the bandgap of a very large number of novel 2D heterostructures. Using this approach, a database of ≈2.2 million bandgap values for various novel 2D van der Waals heterostructures is produced. Active machine learning algorithms are used to leverage a limited number of accurate density functional theory calculations (HSE06) to predict the bandgap of 2.2M novel van der Waals heterostructures.
ISSN:2640-4567
2640-4567
DOI:10.1002/aisy.202100080