Modeling Electronic Quantum Transport with Machine Learning

Abstract

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 datasets 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.

5 pages, 4 figures

Cited by in corpus (30)

• Comparing molecules and solids across structural and alchemical space
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• A Machine Learning Potential for Graphene
• Deep learning and the Schrödinger equation
• Machine learning for many-body physics: The case of the Anderson impurity model
• The Many-Body Expansion Combined with Neural Networks
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Compositional optimization of hard-magnetic phases with machine-learning models
• Machine Learning Prediction of DNA Charge Transport
• Few-shot machine learning in the three-dimensional Ising model
• Classifying surface probe images in strongly correlated electronic systems via machine learning
• Deep learning and high harmonic generation
• Disorder information from conductance: a quantum inverse problem
• Classical and quantum machine learning applications in spintronics
• Machine learning at the atomic-scale
• Nonequilibrium fluctuations of a driven quantum heat engine via machine learning
• Spatial mapping of disordered 2D materials: the conductance Sudoku
• Levy-Lieb principle: The bridge between the electron density of Density Functional Theory and the wavefunction of Quantum Monte Carlo
• AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems
• Decoding the DC and optical conductivities of disordered MoS${}_2$ films: an inverse problem
• Deciphering quantum fingerprints in electric conductance
• Deep Learning Hamiltonians from Disordered Image Data in Quantum Materials
• Predicting magnetic edge behaviour in graphene using neural networks
• Ab initio machine learning in chemical compound space
• Machine learning delta-T noise for temperature bias estimation
• Decoding the conductance of disordered nanostructures: a quantum inverse problem
• Exploring exotic configurations with anomalous features using deep learning: Application of classical and quantum-classical hybrid anomaly detection
• Inverse magneto-conductance design by automatic differentiation
• Scalable Machine Learning Models for Predicting Quantum Transport in Disordered 2D Hexagonal Materials