skip to main content

DOE PAGESDOE PAGES

Title: Modeling Electronic Quantum Transport with Machine Learning

We present a machine learning approach to solve electronic quantum transport equations of one-dimensional nanostructures. The transmission coefficients of disordered systems were computed to provide training and test data sets to the machine. The system’s representation encodes energetic as well as geometrical information to characterize similarities between disordered configurations, while the Euclidean norm is used as a measure of similarity. Errors for out-of-sample predictions systematically decrease with training set size, enabling the accurate and fast prediction of new transmission coefficients. The remarkable performance of our model to capture the complexity of interference phenomena lends further support to its viability in dealing with transport problems of undulatory nature.
Authors:
 [1] ;  [2]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
  2. Argonne National Lab. (ANL), Argonne, IL (United States); Univ. of Basel (Switzerland)
Publication Date:
Grant/Contract Number:
AC02-06CH11357
Type:
Accepted Manuscript
Journal Name:
Physical Review
Additional Journal Information:
Journal Volume: 89; Journal Issue: 23; Journal ID: ISSN 0031-899X
Publisher:
American Physical Society (APS)
Research Org:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org:
USDOE
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING
OSTI Identifier:
1357487

Lopez Bezanilla, Alejandro, and von Lilienfeld Toal, Otto A. Modeling Electronic Quantum Transport with Machine Learning. United States: N. p., Web. doi:10.1103/PhysRevB.89.235411.
Lopez Bezanilla, Alejandro, & von Lilienfeld Toal, Otto A. Modeling Electronic Quantum Transport with Machine Learning. United States. doi:10.1103/PhysRevB.89.235411.
Lopez Bezanilla, Alejandro, and von Lilienfeld Toal, Otto A. 2014. "Modeling Electronic Quantum Transport with Machine Learning". United States. doi:10.1103/PhysRevB.89.235411. https://www.osti.gov/servlets/purl/1357487.
@article{osti_1357487,
title = {Modeling Electronic Quantum Transport with Machine Learning},
author = {Lopez Bezanilla, Alejandro and von Lilienfeld Toal, Otto A.},
abstractNote = {We present a machine learning approach to solve electronic quantum transport equations of one-dimensional nanostructures. The transmission coefficients of disordered systems were computed to provide training and test data sets to the machine. The system’s representation encodes energetic as well as geometrical information to characterize similarities between disordered configurations, while the Euclidean norm is used as a measure of similarity. Errors for out-of-sample predictions systematically decrease with training set size, enabling the accurate and fast prediction of new transmission coefficients. The remarkable performance of our model to capture the complexity of interference phenomena lends further support to its viability in dealing with transport problems of undulatory nature.},
doi = {10.1103/PhysRevB.89.235411},
journal = {Physical Review},
number = 23,
volume = 89,
place = {United States},
year = {2014},
month = {6}
}