Reconstructing the potential configuration in a high-mobility semiconductor heterostructure with scanning gate microscopy

TL;DR

This paper demonstrates that scanning gate microscopy combined with machine learning can accurately reconstruct the disorder potential in high-mobility semiconductor heterostructures, aiding in understanding and improving nanodevice performance.

Contribution

It introduces a novel machine learning method to reconstruct the disorder potential from SGM data, providing a new tool for analyzing high-mobility semiconductor heterostructures.

Findings

Successful reconstruction of electric potential from experimental SGM data

Validation of the reconstruction accuracy through independent estimates

Potential for improved nanodevice design and analysis

Abstract

The weak disorder potential seen by the electrons of a two-dimensional electron gas in high-mobility semiconductor heterostructures leads to fluctuations in the physical properties and can be an issue for nanodevices. In this paper, we show that a scanning gate microscopy (SGM) image contains information about the disorder potential, and that a machine learning approach based on SGM data can be used to determine the disorder. We reconstruct the electric potential of a sample from its experimental SGM data and validate the result through an estimate of its accuracy.