Modeling electronic quantum transport with machine learning

@article{LopezBezanilla2014ModelingEQ,
  title={Modeling electronic quantum transport with machine learning},
  author={Alejandro Lopez-Bezanilla and O. Anatole von Lilienfeld},
  journal={Physical Review B},
  year={2014},
  volume={89},
  pages={235411}
}
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… 

Figures from this paper

Nonequilibrium fluctuations of a driven quantum heat engine via machine learning.
TLDR
It is observed that the standard thermodynamic uncertainty relation is not valid when there are finite geometric contributions to the fluctuations but holds true for zero phase difference even in the presence of coherences.
Neural networks for modeling electron transport properties of mesoscopic systems
TLDR
This work trains neural networks to predict transport properties of a quasi-one-dimensional tight-binding model with disordered on-site energies and finds that even for a relatively large system size, the trained neural network in model II performs much better in predicting the conductance at the Fermi energy.
First-Principles Prediction of Electronic Transport in Experimental Semiconductor Heterostructures via Physics-Based Machine Learning
First-principles techniques for electronic transport property prediction have seen rapid progress in recent years. However, it remains a challenge to model heterostructures incorporating variability
Machine learning on the electron–boson mechanism in superconductors
TLDR
It is proposed that the machine learning might infer pairing mechanism from observables like superconducting gap functions to extract relevant information from data and can be applied to general function-to-function mappings with asymmetric complexities either in physics or other fields.
Machine Learning Prediction of DNA Charge Transport.
TLDR
A machine learning model is presented that allows the inexpensive prediction of the electrical conductance of millions of long double-stranded DNA (dsDNA) sequences, reducing computational costs by orders of magnitude and supports physical observations that clusters of nucleotides regulate DNA transport behavior.
Electronic spectra from TDDFT and machine learning in chemical space.
TLDR
This work applies machine learning models trained on deviations of reference second-order approximate coupled-cluster singles and doubles spectra from TDDFT counterparts, or even from DFT gap to low-lying singlet-singlet vertical electronic spectra of over 20 000 synthetically feasible small organic molecules with up to eight CONF atoms.
Disorder information from conductance: A quantum inverse problem
It is straightforward to calculate the conductance of a quantum device once all its scattering centers are fully specified. However, to do this in reverse, i.e., to find information about the
Ab Initio Machine Learning in Chemical Compound Space
TLDR
While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.
Development of a machine learning potential for graphene
© 2018 American Physical Society. We present an accurate interatomic potential for graphene, constructed using the Gaussian approximation potential (GAP) machine learning methodology. This GAP model
...
...

References

SHOWING 1-10 OF 31 REFERENCES
Fast and accurate modeling of molecular atomization energies with machine learning.
TLDR
A machine learning model is introduced to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only, and applicability is demonstrated for the prediction of molecular atomization potential energy curves.
Accelerating materials property predictions using machine learning
TLDR
It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions.
Four-terminal phase-coherent conductance.
A conductance formula for a sample of arbitrary shape with four terminals is derived to describe transport in the limit where carriers can traverse the sample without suffering phase-destroying
The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition
TLDR
This major new edition features many topics not covered in the original, including graphical models, random forests, ensemble methods, least angle regression and path algorithms for the lasso, non-negative matrix factorization, and spectral clustering.
IBM journal of research and development: information for authors
TLDR
Background information about the IBM Journal of Research and Development is combined with guidelines for the preparation of Journal manuscripts to acquaint authors with the Journal as a primary, professional publication and to present suggestions to ease the work of author and editor in preparing clear, concise, and useful manuscripts.
Electrical resistance of disordered one-dimensional lattices
(1970). Electrical resistance of disordered one-dimensional lattices. The Philosophical Magazine: A Journal of Theoretical Experimental and Applied Physics: Vol. 21, No. 172, pp. 863-867.
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
TLDR
This book is a valuable resource, both for the statistician needing an introduction to machine learning and related Ž elds and for the computer scientist wishing to learn more about statistics, and statisticians will especially appreciate that it is written in their own language.
Finding Nature’s Missing Ternary Oxide Compounds Using Machine Learning and Density Functional Theory
Finding new compounds and their crystal structures is an essential step to new materials discoveries. We demonstrate how this search can be accelerated using a combination of machine learning
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.
TLDR
A number of established machine learning techniques are outlined and the influence of the molecular representation on the methods performance is investigated, finding the best methods achieve prediction errors of 3 kcal/mol for the atomization energies of a wide variety of molecules.
...
...