Deep neural networks for inverse problems in mesoscopic physics: Characterization of the disorder configuration from quantum transport properties
arXiv:2106.11623 · doi:10.1103/PhysRevB.104.075422
Abstract
We present a machine learning approach that allows to characterize the disorder potential of a two-dimensional electronic system from its quantum transport properties. Numerically simulated transport data for a large number of disorder configurations is used for the training of artificial neural networks. We show that the trained networks are able to recognize details of the disorder potential of an unknown sample from its transport properties, and that they can even reconstruct the complete potential landscape seen by the electrons.
arXiv commentfinal version; 13 pages, 11 figures
References in corpus (14)
- Machine learning and the physical sciences
- Kwant: a software package for quantum transport
- Discovering physical concepts with neural networks
- Coherent Branched Flow in a Two-Dimensional Electron Gas
- On the imaging of electron transport in semiconductor quantum structures by scanning-gate microscopy: successes and limitations
- Electron interferometer formed with a scanning probe tip and quantum point contact
- What is measured in the scanning gate microscopy of a quantum point contact?
- Theory of scanning gate microscopy
- Local densities, distribution functions, and wave function correlations for spatially resolved shot noise at nanocontacts
- Scanning gate experiments: from strongly to weakly invasive probes
- Partial local density of states from scanning gate microscopy
- Energy Stability of Branching in the Scanning Gate Response of Two-Dimensional Electron Gases with Smooth Disorder
- Stable Branched Electron Flow
- Signatures of folded branches in the scanning gate microscopy of ballistic electronic cavities
Cited by in corpus (5)
- Unveiling the charge distribution of a GaAs-based nanoelectronic device: A large experimental data-set approach
- Bridging the reality gap in quantum devices with physics-aware machine learning
- Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
- Reconstructing the potential configuration in a high-mobility semiconductor heterostructure with scanning gate microscopy
- Differentiable master equation solver for quantum device characterisation