Diffusion model for analyzing quantum fingerprints in conductance fluctuation

TL;DR

This paper introduces a conditional diffusion model that leverages machine learning to analyze and reconstruct quantum fingerprints in conductance fluctuations, revealing impurity configurations and interference patterns from magnetoconductance data.

Contribution

The study presents a novel diffusion-based machine learning approach for analyzing quantum conductance fluctuations and visualizes attention and score functions to interpret electron wave correlations.

Findings

Successfully reconstructs impurity arrangements from data

Visualizes non-local electron wave correlations

Provides a new tool for quantum transport analysis

Abstract

A conditional diffusion model has been developed to analyze intricate conductance fluctuations called universal conductance fluctuations or quantum fingerprints appearing in quantum transport phenomena. The model reconstructs impurity arrangements and quantum interference patterns in nanometals by using magnetoconductance data, providing a novel approach to analyze complex data based on machine learning. In addition, we visualize the attention weights in the model, which efficiently extract information on the non-local correlation of the electron wave functions, and the score functions, which represent the force fields in the wave-function space.